---
language:
- en
license: llama3
tags:
- Llama-3.1
- instruct
- finetune
- reasoning
- hybrid-mode
- chatml
- function calling
- tool use
- json mode
- structured outputs
- atropos
- dataforge
- long context
- roleplaying
- chat
- mlx
- mlx
- mlx-my-repo
base_model: mlx-community/Hermes-4-70B-5bit
library_name: mlx
widget:
- example_title: Hermes 4
  messages:
  - role: system
    content: You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise,
      correct answers.
  - role: user
    content: Explain the difference between BFS and DFS to a new CS student.
pipeline_tag: text-generation
model-index:
- name: Hermes-4-Llama-3.1-70B
  results: []
---

# introvoyz041/Hermes-4-70B-5bit-mlx-8Bit

The Model [introvoyz041/Hermes-4-70B-5bit-mlx-8Bit](https://huggingface.co/introvoyz041/Hermes-4-70B-5bit-mlx-8Bit) was converted to MLX format from [mlx-community/Hermes-4-70B-5bit](https://huggingface.co/mlx-community/Hermes-4-70B-5bit) using mlx-lm version **0.28.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("introvoyz041/Hermes-4-70B-5bit-mlx-8Bit")

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)
```