Downloads · 30 days
30
8% of all-time downloads
Llama-3-6B-Instruct-pruned-mlx-4bit
typealias/Llama-3-6B-Instruct-pruned-mlx-4bit
Llama-3-6B-Instruct-pruned-mlx-4bit is a text generation model from typealias. Use it when you need the model to write or continue text. It is set up for transformers.
The Model typealias/Llama-3-6B-Instruct-pruned-mlx-4bit was converted to MLX format from kuotient/Llama-3-6B-Instruct-pruned using mlx-lm version 0.13.0.
All-time downloads
391
Public
Parameters
6.3B
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.5 GB · 100%
Parameter types
How the weights are stored.
U326.3B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
typealias/Llama-3-6B-Instruct-pruned-mlx-4bit
The Model typealias/Llama-3-6B-Instruct-pruned-mlx-4bit was converted to MLX format from kuotient/Llama-3-6B-Instruct-pruned using mlx-lm version 0.13.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("typealias/Llama-3-6B-Instruct-pruned-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- May 15, 2024
- Updated
- May 15, 2024