Transformers
GGUF
English
quantized
roleplay
imatrix
mistral

This repository hosts GGUF-Imatrix quantizations for ChaoticNeutrals/Eris_Floramix_DPO_7B.

Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
    quantization_options = [
        "Q3_K_M", "Q4_K_M", "Q5_K_M", "Q6_K",
        "Q8_0", "IQ4_XS", "IQ3_XXS"
    ]

This is experimental.

For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used, you can find it here.

The goal is to measure the (hopefully positive) impact of this data for consistent formatting in roleplay chatting scenarios.

Image:

image/png

Original model information:

Eris Floramix DPO

This is a mix between Eris Remix DPO and Flora DPO, a finetune of the original Eris Remix on the Synthetic_Soul_1k dataset.

Applied this DPO dataset: https://huggingface.co/datasets/athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v1-SHUFFLED

Downloads last month
141
GGUF
Model size
7.24B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model authors have turned it off explicitly.

Datasets used to train Lewdiculous/Eris_Floramix_DPO_7B-GGUF-Imatrix

Collection including Lewdiculous/Eris_Floramix_DPO_7B-GGUF-Imatrix