---
license: llama3.1
base_model: cognitivecomputations/dolphin-2.9.4-llama3.1-8b
tags:
- generated_from_trainer
- mlx
datasets:
- cognitivecomputations/Dolphin-2.9
- m-a-p/CodeFeedback-Filtered-Instruction
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- microsoft/orca-math-word-problems-200k
- mlabonne/FineTome-100k
- arcee/agent_data
- PawanKrd/math-gpt-4o-200k
- cognitivecomputations/SystemChat-2.0
---

# mlx-community/dolphin-2.9.4-llama3.1-8b-4bit

The Model [mlx-community/dolphin-2.9.4-llama3.1-8b-4bit](https://huggingface.co/mlx-community/dolphin-2.9.4-llama3.1-8b-4bit) was converted to MLX format from [cognitivecomputations/dolphin-2.9.4-llama3.1-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9.4-llama3.1-8b) using mlx-lm version **0.19.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/dolphin-2.9.4-llama3.1-8b-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)
```