glm-edge-4b-chat_a137939873.../README.md

64 lines
1.2 KiB
Markdown

---
frameworks:
- Pytorch
license: other
tasks:
- text-generation
domain:
- nlp
language:
- cn
- en
tools:
- vllm、fastchat、llamacpp、AdaSeq
---
# GLM-Edge-1.5B-Chat
Read this in [English](README_en.md)
## 使用 transformers 库进行推理
### 安装
请安装源代码的transformers库。
```shell
pip install git+https://github.com/huggingface/transformers.git
```
### 推理
```python
from modelscope import AutoModelForCausalLM, AutoTokenizer
MODEL_PATH = "ZhipuAI/glm-edge-4b-chat"
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, device_map="auto")
message = [{"role": "user", "content": "hello!"}]
inputs = tokenizer.apply_chat_template(
message,
return_tensors="pt",
add_generation_prompt=True,
return_dict=True,
).to(model.device)
generate_kwargs = {
"input_ids": inputs["input_ids"],
"attention_mask": inputs["attention_mask"],
"max_new_tokens": 128,
"do_sample": False,
}
out = model.generate(**generate_kwargs)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
```
## 协议
本模型的权重的使用则需要遵循 [LICENSE](LICENSE)。