GGUF importance matrix (imatrix) quants for https://huggingface.co/jondurbin/bagel-34b-v0.4
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
Prompt strategies: https://huggingface.co/jondurbin/bagel-34b-v0.4#prompting-strategies
Feb. 21, 2024: Updating quants from latest commit.
Layers | Context | Template |
---|---|---|
60 |
200000 |
[INST] <<SYS>> |
- Downloads last month
- 27
Inference API (serverless) does not yet support gguf models for this pipeline type.