Downloads · 30 days
18
15% of all-time downloads
yiwenX/smoltalk-sft-135M-chinese
smoltalk-sft-135M-chinese is a text generation model from yiwenX. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
这是一个基于 SmolLM2-135M 模型使用 SFT (Supervised Fine-Tuning) 方法在 SmolTalk 数据集上微调的中文对话模型。
Downloads · 30 days
18
15% of all-time downloads
All-time downloads
121
Public
Parameters
135M
538 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors538 MB · 99%
From the Hugging Face model README
这是一个基于 SmolLM2-135M 模型使用 SFT (Supervised Fine-Tuning) 方法在 SmolTalk 数据集上微调的中文对话模型。
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "your-username/smoltalk-sft-135M-chinese"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# 生成对话
inputs = tokenizer("你好,请问", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
Apache 2.0
如果你使用了这个模型,请引用原始的 SmolLM2 和 SmolTalk 项目。