Downloads · 30 days
0
dolphin-2.6-mixtral-8x7b-w4a16g128asym_1
numen-tech/dolphin-2.6-mixtral-8x7b-w4a16g128asym_1
dolphin-2.6-mixtral-8x7b-w4a16g128asym_1 is a machine learning model from numen-tech. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
4-bit OmniQuant quantized version of dolphin-2.6-mixtral-8x7b. Note that the embedding and the MoE gate weights are not quantized in this version.
Access
Public
Updated Apr 12, 2024
Repo size
24.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin24.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 12, 2024
- Updated
- Apr 12, 2024
- SHA
- 6269740e
Model card
From the Hugging Face model README
4-bit OmniQuant quantized version of dolphin-2.6-mixtral-8x7b. Note that the embedding and the MoE gate weights are not quantized in this version.
- License
- apache-2.0
- Created
- Apr 12, 2024
- Updated
- Apr 12, 2024