64 lines
1.4 KiB
Markdown
64 lines
1.4 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
license: llama3
|
||
|
|
tags:
|
||
|
|
- Llama-3
|
||
|
|
- instruct
|
||
|
|
- finetune
|
||
|
|
- chatml
|
||
|
|
- gpt4
|
||
|
|
- synthetic data
|
||
|
|
- distillation
|
||
|
|
- function calling
|
||
|
|
- json mode
|
||
|
|
- axolotl
|
||
|
|
- roleplaying
|
||
|
|
- chat
|
||
|
|
- reasoning
|
||
|
|
- r1
|
||
|
|
- vllm
|
||
|
|
- mlx
|
||
|
|
base_model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
|
||
|
|
widget:
|
||
|
|
- example_title: Hermes 3
|
||
|
|
messages:
|
||
|
|
- role: system
|
||
|
|
content: You are a sentient, superintelligent artificial general intelligence,
|
||
|
|
here to teach and assist me.
|
||
|
|
- role: user
|
||
|
|
content: What is the meaning of life?
|
||
|
|
library_name: transformers
|
||
|
|
model-index:
|
||
|
|
- name: DeepHermes-3-Llama-3.1-8B
|
||
|
|
results: []
|
||
|
|
---
|
||
|
|
|
||
|
|
# mlx-community/DeepHermes-3-Llama-3-8B-Preview-bf16
|
||
|
|
|
||
|
|
The Model [mlx-community/DeepHermes-3-Llama-3-8B-Preview-bf16](https://huggingface.co/mlx-community/DeepHermes-3-Llama-3-8B-Preview-bf16) was
|
||
|
|
converted to MLX format from [NousResearch/DeepHermes-3-Llama-3-8B-Preview](https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview)
|
||
|
|
using mlx-lm version **0.21.1**.
|
||
|
|
|
||
|
|
## Use with mlx
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install mlx-lm
|
||
|
|
```
|
||
|
|
|
||
|
|
```python
|
||
|
|
from mlx_lm import load, generate
|
||
|
|
|
||
|
|
model, tokenizer = load("mlx-community/DeepHermes-3-Llama-3-8B-Preview-bf16")
|
||
|
|
|
||
|
|
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)
|
||
|
|
```
|