Downloads · 30 days
4
11% of all-time downloads
woohello/olmo3-190m-zh-sft
olmo3-190m-zh-sft is a machine learning model from woohello. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
SFT (有监督微调) 版本:基于 woohello/olmo3-190m-zh-nano 继续 SFT, 学习指令遵循能力,从"续写文本"转向"扮演 assistant 回答"。
Downloads · 30 days
4
11% of all-time downloads
All-time downloads
36
Public
Parameters
22M
44 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors44 MB · 92%
From the Hugging Face model README
SFT (有监督微调) 版本:基于 woohello/olmo3-190m-zh-nano 继续 SFT,
学习指令遵循能力,从"续写文本"转向"扮演 assistant 回答"。
woohello/olmo3-190m-zh-nano (26M, OLMo3 arch, SDPA)cmz1024/llm101-olmo3-zh-demo-data/sft/sft_t2t_mini.jsonl (对话格式)from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("woohello/olmo3-190m-zh-sft", attn_implementation="sdpa")
tok = AutoTokenizer.from_pretrained("woohello/olmo3-190m-zh-sft")
messages = [{"role": "user", "content": "你好"}]
input_ids = tok.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
out = model.generate(input_ids, max_new_tokens=256, do_sample=True, temperature=0.7)
print(tok.decode(out[0][input_ids.shape[1]:], skip_special_tokens=True))