|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- mistral |
|
- instruct |
|
- finetune |
|
- chatml |
|
- gpt4 |
|
- synthetic data |
|
- distillation |
|
- mlx |
|
datasets: |
|
- teknium/OpenHermes-2.5 |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: OpenHermes-2-Mistral-7B |
|
results: [] |
|
--- |
|
|
|
# cogbuji/OpenHermes-2.5-Mistral-7B-mlx-4bit |
|
This model was converted to MLX format from [teknium/OpenHermes-2.5-Mistral-7B](/teknium/OpenHermes-2.5-Mistral-7B) and quantized. |
|
Refer to the [original model card](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) for more details on the model. |
|
|
|
It was converted and quantized with mlx **0.7.0** and mlx_lm **0.3.0** and should be used with those versions. Later versions of these may deprecate this model |
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("cogbuji/OpenHermes-2.5-Mistral-7B-mlx-4bit") |
|
response = generate(model, tokenizer, prompt="hello", verbose=True) |
|
``` |
|
|
