lb-reranker-0.5B-v1.0

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

from vllm import LLM, SamplingParams
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id].logprob) if tok_id in logprob_dict.keys() else 0

llm = LLM("lightblue/lb-reranker-v1.0")
sampling_params = SamplingParams(temperature=0.0, logprobs=14, max_tokens=1)
tok = llm.llm_engine.tokenizer.tokenizer
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = llm.chat(chats, sampling_params)
probs = np.array([[get_prob(r.outputs[0].logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66570732 1.86686378 1.01102923]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

# Un-comment this if running in a Jupyter notebook, Colab etc.
# import nest_asyncio
# nest_asyncio.apply()

from lmdeploy import GenerationConfig, ChatTemplateConfig, pipeline
import numpy as np

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_prob(logprob_dict, tok_id):
    return np.exp(logprob_dict[tok_id]) if tok_id in logprob_dict.keys() else 0

pipe = pipeline(
    "lightblue/lb-reranker-v1.0",
    chat_template_config=ChatTemplateConfig(
                    model_name='qwen2d5',
                    capability='chat'
    )
)
tok = pipe.tokenizer.model
idx_tokens = [tok.encode(str(i))[0] for i in range(1, 8)]

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

chats = [make_reranker_inference_conversation(c, q) for q, c in query_texts]
responses = pipe(
    chats, 
    gen_config=GenerationConfig(temperature=1.0, logprobs=14, max_new_tokens=1, do_sample=True)
)
probs = np.array([[get_prob(r.logprobs[0], y) for y in idx_tokens] for r in responses])

N = probs.shape[1]
M = probs.shape[0]
idxs = np.tile(np.arange(1, N + 1), M).reshape(M, N)

expected_vals = (probs * idxs).sum(axis=1)
print(expected_vals)
# [6.66415229 1.84342025 1.01133205]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]

from openai import OpenAI
import numpy as np
from multiprocessing import Pool
from tqdm.auto import tqdm

client = OpenAI(
	base_url="https://api-inference.huggingface.co/v1/",
	api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Change this to an access token from https://huggingface.co/settings/tokens
)

def make_reranker_input(t, q):
    return f"<<<Query>>>\n{q}\n\n<<<Context>>>\n{t}"

def make_reranker_inference_conversation(context, question):
    system_message = "Given a query and a piece of text, output a score of 1-7 based on how related the query is to the text. 1 means least related and 7 is most related."

    return [
        {"role": "system", "content": system_message},
        {"role": "user", "content": make_reranker_input(context, question)},
    ]

def get_reranker_score(context_question_tuple):
    question, context = context_question_tuple

    messages = make_reranker_inference_conversation(context, question)

    completion = client.chat.completions.create(
        model="lightblue/lb-reranker-0.5B-v1.0", 
        messages=messages,
        max_tokens=1,
        temperature=0.0,
        logprobs=True,
        top_logprobs=5, # Max allowed by the openai API as top_n_tokens must be >= 0 and <= 5. If this gets changed, fix to > 7.
    )

    logprobs = completion.choices[0].logprobs.content[0].top_logprobs

    calculated_score = sum([int(x.token) * np.exp(x.logprob) for x in logprobs])

    return calculated_score

query_texts = [
    ("What is the scientific name of apples?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the Chinese word for 'apple'?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
    ("What is the square root of 999?", "An apple is a round, edible fruit produced by an apple tree (Malus spp., among them the domestic or orchard apple; Malus domestica)."),
]

with Pool(processes=16) as p: # Allows for parallel processing
    expected_vals = list(tqdm(p.imap(get_reranker_score, query_texts), total=len(query_texts)))

print(expected_vals)
# [6.64866580, 1.85144404, 1.010719508]