Configuration Parsing Warning: In config.json: "quantization_config.bits" must be an integer

image/png

Mistral-Small-Gutenberg-Doppel-22B - EXL2 6.8bpw

This is a 6.8bpw EXL2 quant of nbeerbower/Mistral-Small-Gutenberg-Doppel-22B

This quant was made using exllamav2-0.2.2 with default dataset.

I tested this quant shortly in some random RPs (including some RPs with 8k+ context) and it seems to work fine.

Prompt Templates

Uses Mistral v2/v3 format.

Original readme below


Mistral-Small-Gutenberg-Doppel-22B

mistralai/Mistral-Small-Instruct-2409 finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.

Method

ORPO tuned with an A40 on RunPod (plz sponsor me) for 3 epochs.

Fine-tune Llama 3 with ORPO

Downloads last month
1
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for DeusImperator/Mistral-Small-Gutenberg-Doppel-22B_exl2_6.8bpw

Datasets used to train DeusImperator/Mistral-Small-Gutenberg-Doppel-22B_exl2_6.8bpw