|
|
--- |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- PrimeIntellect/Intellect-2-RL-Dataset |
|
|
base_model: PrimeIntellect/INTELLECT-2 |
|
|
library_name: mlx |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- mlx |
|
|
--- |
|
|
|
|
|
# leonsarmiento/INTELLECT-2-8bit-mlx |
|
|
|
|
|
This model [leonsarmiento/INTELLECT-2-8bit-mlx](https://huggingface.co/leonsarmiento/INTELLECT-2-8bit-mlx) was |
|
|
converted to MLX format from [PrimeIntellect/INTELLECT-2](https://huggingface.co/PrimeIntellect/INTELLECT-2) |
|
|
using mlx-lm version **0.28.3**. |
|
|
|
|
|
Recommended Parameters: |
|
|
|
|
|
Temperature: 0.6 |
|
|
Top K: 30 |
|
|
Repeat penalty: 1.1 |
|
|
Min P sampling: 0 |
|
|
Top P sampling: 0.95 |
|
|
|
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
from mlx_lm import load, generate |
|
|
|
|
|
model, tokenizer = load("leonsarmiento/INTELLECT-2-8bit-mlx") |
|
|
|
|
|
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) |
|
|
``` |
|
|
|
