solar-10.7b-4bit / README.md
shashikanth-a's picture
0918383210cdf1a6375a2d0dace8b69f96c99a213e9960d7fcb828dc40f6018b
d0d9ff8 verified
|
raw
history blame
844 Bytes
---
license: apache-2.0
base_model: upstage/SOLAR-10.7B-v1.0
tags:
- mlx
---
# shashikanth-a/solar-10.7b-4bit
The Model [shashikanth-a/solar-10.7b-4bit](https://huggingface.co/shashikanth-a/solar-10.7b-4bit) was converted to MLX format from [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) using mlx-lm version **0.19.3**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("shashikanth-a/solar-10.7b-4bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```