|
--- |
|
language: |
|
- en |
|
- zh |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
--- |
|
# Update |
|
**The model is now following the update from GLM-4-9B-Chat and now requires `transformers>=4.44.0`. Please update your dependencies accordingly.** |
|
**Also follow the [dependencies](https://github.com/THUDM/GLM-4/blob/main/basic_demo/requirements.txt) it before using** |
|
|
|
# Introduction |
|
This model is [GLM-4-9B-Chat](https://huggingface.co/THUDM/glm-4-9b-chat/tree/main), fine-tuned with the [Smile dataset](https://github.com/qiuhuachuan/smile) to focus on mental health care. |
|
|
|
Since it is fine-tuned with a Chinese dataset, please use it in Chinese, even though the base model supports English text. |
|
|
|
# Use the following method to quickly call the GLM-4-9B-Chat language model |
|
Use the transformers backend for inference: |
|
```python |
|
import torch |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
device = "cuda" |
|
tokenizer = AutoTokenizer.from_pretrained("derek33125/project-angel-chatglm4", trust_remote_code=True) |
|
query = "我感到很悲伤" |
|
inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}], |
|
add_generation_prompt=True, |
|
tokenize=True, |
|
return_tensors="pt", |
|
return_dict=True |
|
) |
|
inputs = inputs.to(device) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
"derek33125/project-angel-chatglm4", |
|
torch_dtype=torch.bfloat16, |
|
low_cpu_mem_usage=True, |
|
trust_remote_code=True |
|
).to(device).eval() |
|
gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1} |
|
with torch.no_grad(): |
|
outputs = model.generate(**inputs, **gen_kwargs) |
|
outputs = outputs[:, inputs['input_ids'].shape[1]:] |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
It also supports [VLLM](https://github.com/THUDM/GLM-4/blob/main/basic_demo/openai_api_server.py) and [LangChain](https://python.langchain.com/v0.2/docs/integrations/llms/huggingface_pipelines/) . |
|
|
|
|
|
|
