Upload folder using huggingface_hub
Browse files- README.md +23 -0
- tokenizer.model +0 -0
README.md
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- code
|
4 |
+
license: llama2
|
5 |
+
tags:
|
6 |
+
- llama-2
|
7 |
+
- mlx
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
---
|
10 |
+
|
11 |
+
# CodeLlama-7b-Python-hf-4bit
|
12 |
+
|
13 |
+
This model was converted to MLX format from codellama/CodeLlama-7b-Python-hf. Please, refer to the [original model card](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) for more details on the original model.
|
14 |
+
|
15 |
+
## Use with mlx
|
16 |
+
|
17 |
+
```bash
|
18 |
+
pip install mlx
|
19 |
+
git clone https://github.com/ml-explore/mlx-examples.git
|
20 |
+
|
21 |
+
cd mlx-examples/llms/hf_llm
|
22 |
+
python generate.py --model mlx-community/CodeLlama-7b-Python-hf-4bit --prompt "My name is"
|
23 |
+
```
|
tokenizer.model
CHANGED
Binary files a/tokenizer.model and b/tokenizer.model differ
|
|