Light-IF-14B

Name: Light-IF-14B
Author: qihoo360

14.0B

license:apache-2.0

qihoo360

Language Model

OTHER

14B params

New

21 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

32GB+ RAM

Mobile

Laptop

Server

Quick Summary

🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp 📑 Paper Link &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp 📑 Github &nbsp&nbsp | &nbsp&nbsp 📑 SuperCLUE-CPI...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

14GB+ RAM

Code Examples

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Quickstartpythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "qihoo360/Light-IF-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True 
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.