Edit model card

NousResearch_Hermes-2-Pro-Mistral-7B-mlx (8-bit quant)

This model was converted to MLX format from NousResearch/Hermes-2-Pro-Mistral-7B. Refer to the original model card for more details on the model.

8-bit quant:

converted with the following parameters: --q-group-size 128 --q-bits 8 --dtype bfloat16

Downloads last month
2
Safetensors
Model size
2.02B params
Tensor type
FP16
·
U32
·
Inference API
Input a message to start chatting with fbjr/NousResearch_Hermes-2-Pro-Mistral-7B-mlx.
Inference API (serverless) does not yet support mlx models for this pipeline type.

Finetuned from