Add files using upload-large-folder tool
Browse files
README.md
CHANGED
|
@@ -1,38 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
license: mit
|
| 5 |
tags:
|
| 6 |
- mlx
|
| 7 |
-
|
| 8 |
-
- glm_moe_dsa
|
| 9 |
-
- conversational
|
| 10 |
-
- text-generation
|
| 11 |
-
language:
|
| 12 |
-
- en
|
| 13 |
-
- zh
|
| 14 |
---
|
| 15 |
-
|
| 16 |
-
# mlx-community/GLM-5
|
| 17 |
-
|
| 18 |
-
This model was converted to MLX format from [`zai-org/GLM-5`](https://huggingface.co/zai-org/GLM-5).
|
| 19 |
-
|
| 20 |
-
GLM-5 is a 744B parameter (40B active) Mixture-of-Experts model developed by Z.ai, targeting complex systems engineering and long-horizon agentic tasks.
|
| 21 |
-
|
| 22 |
-
## Use with mlx-lm
|
| 23 |
-
|
| 24 |
-
```python
|
| 25 |
-
from mlx_lm import load, generate
|
| 26 |
-
|
| 27 |
-
model, tokenizer = load("mlx-community/GLM-5")
|
| 28 |
-
|
| 29 |
-
prompt = "hello"
|
| 30 |
-
|
| 31 |
-
if tokenizer.chat_template is not None:
|
| 32 |
-
messages = [{"role": "user", "content": prompt}]
|
| 33 |
-
prompt = tokenizer.apply_chat_template(
|
| 34 |
-
messages, add_generation_prompt=True
|
| 35 |
-
)
|
| 36 |
-
|
| 37 |
-
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 38 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
+
pipeline_tag: text-generation
|
|
|
|
| 4 |
tags:
|
| 5 |
- mlx
|
| 6 |
+
library_name: mlx
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|