This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 A curated, decontaminated subset of datasets used have been mentioned in the model card. All used datasets are public as of the time of release of this model.

Collaborate or Consult me - Twitter, Discord

Recommended format is ChatML, Alpaca will work but take care of EOT token

Chat Model Inference

Model description

First generic model of Project PIC (Partner-in-Crime) in 7B range. Trying a bunch of things and seeing what sticks right now.

Empathy + Coder + Instruction/json/function adherence is my game. Finding lots of challenges and insights in this effort, patience is key.

Intended uses & limitations

Should be useful in generic capacity. Demonstrates little bit of everything.

Basic tests in - Roleplay: Adherence to character present. json/function-calling: Passing Coding: To be evaluated

Training procedure

SFT + DPO

Training results

Humaneval and evalplus results to be shared as well.

Framework versions

Transformers 4.35.2
Pytorch 2.0.1
Datasets 2.15.0
Tokenizers 0.15.0

SinanAkkoyun/pic_7B_mistral_Full_v0.2-awq

pic_7B_mistral_Full_v0.2