Downloads · 30 days
26
7% of all-time downloads
dolphin-2.9.1-qwen-110b-4bit
mlx-community/dolphin-2.9.1-qwen-110b-4bit
dolphin-2.9.1-qwen-110b-4bit is a machine learning model from mlx-community. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as other.
This model was converted to MLX format from cognitivecomputations/dolphin-2.9.1-qwen-110b using mlx-lm version 0.12.1. Refer to the original model card for more details on the model.
All-time downloads
388
Public
Parameters
111B
62.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors62.6 GB · 100%
Parameter types
How the weights are stored.
U32111B · 100%
Base models
Model card
From the Hugging Face model README
mlx-community/dolphin-2.9.1-qwen-110b-4bit
This model was converted to MLX format from cognitivecomputations/dolphin-2.9.1-qwen-110b using mlx-lm version 0.12.1.
Refer to the original model card for more details on the model.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/dolphin-2.9.1-qwen-110b-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Library
- mlx
- Type
- qwen2
- License
- other
- Created
- May 12, 2024
- Updated
- May 13, 2024