Air-Striker-Mixtral-8x7B-ZLoss

Experimental model, trained using config and Transformers/Axolotl forks provided by Doctor-Shotgun

Model was fine-tuned from Mixtral-8x7B-v0.1 with airoboros-3.2 dataset, for 4 epochs, ChatML prompt format at 8K context length.

GGUF

Model size

46.7B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

Inference Examples

Inference API (serverless) has been turned off for this model.

LoneStriker
/

Air-Striker-Mixtral-8x7B-ZLoss-GGUF