22B AWQ
Collection
These models are selected for their compatibility with 2 small 12GB GPUs, or 1 medium 24GB GPU.
•
2 items
•
Updated
Vezora/Mistral-22B-v0.1 AWQ
- Model creator: Vezora
- Original model: Mistral-22B-v0.2
Model Summary
- Just two days after our release of Mistral-22b-v0.1, we are excited to introduce our handcrafted experimental model, Mistral-22b-v.02. This model is a culmination of equal knowledge distilled from all experts into a single, dense 22b model. This model is not a single trained expert, rather its a compressed MOE model, turning it into a dense 22b mode. This is the first working MOE to Dense model conversion.
- v0.2 has trained on 8x more data than v0.1!
How to use
GUANACO PROMPT FORMAT YOU MUST USE THE GUANACO PROMPT FORMAT SHOWN BELOW. Not using this prompt format will lead to sub optimal results.
- This model requires a specific chat template, as the training format was Guanaco this is what it looks like:
- "### System: You are a helpful assistant. ### Human###: Give me the best chili recipe you can ###Assistant: Here is the best chili recipe..."
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.
Model tree for solidrust/Mistral-22B-v0.2-AWQ
Base model
Vezora/Mistral-22B-v0.2