45 lines
1003 B
Markdown
45 lines
1003 B
Markdown
---
|
|
license: other
|
|
license_name: glm-4
|
|
license_link: https://huggingface.co/THUDM/glm-4-9b-chat-hf/blob/main/LICENSE
|
|
language:
|
|
- en
|
|
- zh
|
|
base_model: zai-org/glm-4-9b-chat-1m-hf
|
|
pipeline_tag: text-generation
|
|
library_name: mlx
|
|
tags:
|
|
- chatglm
|
|
- mlx
|
|
inference: false
|
|
---
|
|
|
|
|
|
# mlx-community/glm-4-9b-chat-1m-bf16
|
|
|
|
This model [mlx-community/glm-4-9b-chat-1m-bf16](https://huggingface.co/mlx-community/glm-4-9b-chat-1m-bf16) was
|
|
converted to MLX format from [zai-org/glm-4-9b-chat-1m-hf](https://huggingface.co/zai-org/glm-4-9b-chat-1m-hf)
|
|
using mlx-lm version **0.27.1**.
|
|
|
|
## Use with mlx
|
|
|
|
```bash
|
|
pip install mlx-lm
|
|
```
|
|
|
|
```python
|
|
from mlx_lm import load, generate
|
|
|
|
model, tokenizer = load("mlx-community/glm-4-9b-chat-1m-bf16")
|
|
|
|
prompt = "hello"
|
|
|
|
if tokenizer.chat_template is not None:
|
|
messages = [{"role": "user", "content": prompt}]
|
|
prompt = tokenizer.apply_chat_template(
|
|
messages, add_generation_prompt=True
|
|
)
|
|
|
|
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
|
```
|