rank1-mistral-2501-24b-awq

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from vllm import LLM, SamplingParams
import math

# Initialize the model with vLLM
model = LLM(
    model="jhu-clsp/rank1-mistral-2501-24b-awq",
    tensor_parallel_size=1,  # Number of GPUs
    trust_remote_code=True,
    max_model_len=16000,     # Context length
    gpu_memory_utilization=0.9,
    dtype="auto",  # Will use the appropriate quantized dtype
)

# Set up sampling parameters
sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
    skip_special_tokens=False
)

# Prepare the prompt
def create_prompt(query, document):
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {document}\n"
        "<think>"
    )

# Example usage
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

# Generate prediction
prompt = create_prompt(query, document)
outputs = model.generate([prompt], sampling_params)

# Extract score
output = outputs[0].outputs[0]
text = output.text
final_logits = output.logprobs[-1]

# Get token IDs for "true" and "false" tokens
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]

# Calculate relevance score (probability of "true")
true_logit = final_logits[true_token].logprob
false_logit = final_logits[false_token].logprob
true_score = math.exp(true_logit)
false_score = math.exp(false_logit)
relevance_score = true_score / (true_score + false_score)

print(f"Reasoning chain: {text}")
print(f"Relevance score: {relevance_score}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the tokenizer and quantized model
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-mistral-2501-24b-awq")
model = AutoModelForCausalLM.from_pretrained(
    "jhu-clsp/rank1-mistral-2501-24b-awq",
    device_map="auto",
    trust_remote_code=True
)

# Prepare the prompt
query = "What are the effects of climate change?"
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."

prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n<think>"

# Generate the reasoning chain and relevance judgment
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.0,
        return_dict_in_generate=True,
        output_scores=True,
        pad_token_id=tokenizer.eos_token_id
    )

# Process the output
generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False)
reasoning_chain = generated_text.split("<think>")[1].split("</think>")[0].strip()
relevance_judgment = "true" if "true" in generated_text.split("</think>")[1].strip().lower() else "false"

print(f"Reasoning chain: {reasoning_chain}")
print(f"Relevance judgment: {relevance_judgment}")

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

from mteb import MTEB
from rank1 import rank1  # From the official repo

# Initialize the model
model = rank1(
    model_name_or_path="jhu-clsp/rank1-mistral-2501-24b-awq",
    num_gpus=1,
    device="cuda",
    quantized=True  # Indicate that you're using the quantized version
)

# Run evaluation on specific tasks
evaluation = MTEB(tasks=["NevIR"])
results = evaluation.run(model)

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}

@misc{weller2025rank1testtimecomputereranking,
      title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, 
      author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
      year={2025},
      eprint={2502.18418},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.18418}, 
}