GGUF importance matrix (imatrix) quants for https://huggingface.co./ibivibiv/alpaca-dragon-72b-v1
The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
Layers | Context | Template |
---|---|---|
80 |
32768 |
### Instruction: |
- Downloads last month
- 35
Inference API (serverless) does not yet support gguf models for this pipeline type.