Views
No views yet
| Parameter | Value |
|---|---|
| direction_index | 12.64 |
| attn.o_proj.max_weight | 1.24 |
| attn.o_proj.max_weight_position | 20.95 |
| attn.o_proj.min_weight | 1.21 |
| attn.o_proj.min_weight_distance | 10.38 |
| mlp.down_proj.max_weight | 1.04 |
| mlp.down_proj.max_weight_position | 22.12 |
| mlp.down_proj.min_weight | 0.88 |
| mlp.down_proj.min_weight_distance | 16.83 |
| Metric | This model | Original model (Nanbeige/Nanbeige4-3B-Thinking-2511) |
|---|---|---|
| KL divergence | 0.0024 | 0 (by definition) |
| Refusals | 11/100 | 93/100 |
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
'Nanbeige/Nanbeige4-3B-Thinking-2511',
use_fast=False,
trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
'Nanbeige/Nanbeige4-3B-Thinking-2511',
torch_dtype='auto',
device_map='auto',
trust_remote_code=True
)
messages = [
{'role': 'user', 'content': 'Which number is bigger, 9.11 or 9.8?'}
]
prompt = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=False
)
input_ids = tokenizer(prompt, add_special_tokens=False, return_tensors='pt').input_ids
output_ids = model.generate(input_ids.to('cuda'), eos_token_id=166101)
resp = tokenizer.decode(output_ids[0][len(input_ids[0]):], skip_special_tokens=True)
print(resp)from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
'Nanbeige/Nanbeige4-3B-Thinking-2511',
use_fast=False,
trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
'Nanbeige/Nanbeige4-3B-Thinking-2511',
torch_dtype='auto',
device_map='auto',
trust_remote_code=True
)
messages = [
{'role': 'user', 'content': 'Help me check the weather in Beijing now'}
]
tools = [{'type': 'function',
'function': {'name': 'SearchWeather',
'description': 'Find out current weather in a certain place on a certain day.',
'parameters': {'type': 'dict',
'properties': {'location': {'type': 'string',
'description': 'A city in china.'},
'required': ['location']}}}}]
prompt = tokenizer.apply_chat_template(
messages,
tools,
add_generation_prompt=True,
tokenize=False
)
input_ids = tokenizer(prompt, add_special_tokens=False, return_tensors='pt').input_ids
output_ids = model.generate(input_ids.to('cuda'), eos_token_id=166101)
resp = tokenizer.decode(output_ids[0][len(input_ids[0]):], skip_special_tokens=True)
print(resp)@misc{yang2025nanbeige43btechnicalreportexploring,
title={Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models},
author={Chen Yang and Guangyue Peng and Jiaying Zhu and Ran Le and Ruixiang Feng and Tao Zhang and Wei Ruan and Xiaoqi Liu and Xiaoxue Cheng and Xiyun Xu and Yang Song and Yanzipeng Gao and Yiming Jia and Yun Xing and Yuntao Wen and Zekai Wang and Zhenwei An and Zhicong Sun and Zongchao Chen},
year={2025},
eprint={2512.06266},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2512.06266},
}