Llama-3-8B-Instruct-262k-un…/README.md

---
language:
- en
tags:
- meta
- llama-3
- mlx
pipeline_tag: text-generation
---

# mlx-community/Llama-3-8B-Instruct-262k-unquantized
This model was converted to MLX format from [`gradientai/Llama-3-8B-Instruct-262k`]() using mlx-lm version **0.12.0**.
Refer to the [original model card](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Llama-3-8B-Instruct-262k-unquantized")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
System update meta information 2024-12-20 02:39:21 +00:00			`---`
Upload folder using huggingface_hub 2024-12-20 10:46:14 +08:00			`language:`
			`- en`
			`tags:`
			`- meta`
			`- llama-3`
			`- mlx`
			`pipeline_tag: text-generation`
System update meta information 2024-12-20 02:39:21 +00:00			`---`

Upload folder using huggingface_hub 2024-12-20 10:46:14 +08:00			`# mlx-community/Llama-3-8B-Instruct-262k-unquantized`
			This model was converted to MLX format from [`gradientai/Llama-3-8B-Instruct-262k`]() using mlx-lm version 0.12.0.
			`Refer to the [original model card](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k) for more details on the model.`
			`## Use with mlx`

System update meta information 2024-12-20 02:39:21 +00:00			```bash
Upload folder using huggingface_hub 2024-12-20 10:46:14 +08:00			`pip install mlx-lm`
System update meta information 2024-12-20 02:39:21 +00:00			```
Upload folder using huggingface_hub 2024-12-20 10:46:14 +08:00
System update meta information 2024-12-20 02:39:21 +00:00			```python
Upload folder using huggingface_hub 2024-12-20 10:46:14 +08:00			`from mlx_lm import load, generate`
System update meta information 2024-12-20 02:39:21 +00:00
Upload folder using huggingface_hub 2024-12-20 10:46:14 +08:00			`model, tokenizer = load("mlx-community/Llama-3-8B-Instruct-262k-unquantized")`
			`response = generate(model, tokenizer, prompt="hello", verbose=True)`
			```