|
--- |
|
language: |
|
- en |
|
tags: |
|
- mlx |
|
datasets: |
|
- HuggingFaceH4/ultrafeedback_binarized |
|
- allenai/tulu-v2-sft-mixture |
|
base_model: meta-llama/Llama-2-13b-hf |
|
model-index: |
|
- name: tulu-2-dpo-13b |
|
results: [] |
|
--- |
|
|
|
# mlx-community/tulu-2-dpo-13b-4bit-mlx |
|
This model was converted to MLX format from [`allenai/tulu-2-dpo-13b`](). |
|
Refer to the [original model card](https://huggingface.co/allenai/tulu-2-dpo-13b) for more details on the model. |
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/tulu-2-dpo-13b-4bit-mlx") |
|
response = generate(model, tokenizer, prompt="hello", verbose=True) |
|
``` |
|
|
