Downloads · 30 days
96
1% of all-time downloads
Qwen2-7B-Instruct-8bit
mlx-community/Qwen2-7B-Instruct-8bit
Qwen2-7B-Instruct-8bit is a text generation model from mlx-community. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
The Model mlx-community/Qwen2-7B-Instruct-8bit was converted to MLX format from Qwen/Qwen2-7B-Instruct using mlx-lm version 0.14.0.
All-time downloads
6.7K
Public
Parameters
7.6B
8.1 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors8.1 GB · 100%
Parameter types
How the weights are stored.
U327.6B · 100%
Try a prompt
Model card
From the Hugging Face model README
mlx-community/Qwen2-7B-Instruct-8bit
The Model mlx-community/Qwen2-7B-Instruct-8bit was converted to MLX format from Qwen/Qwen2-7B-Instruct using mlx-lm version 0.14.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Qwen2-7B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Task
- Text Generation
- Library
- mlx
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Jun 6, 2024
- Updated
- Jun 6, 2024