koishi-8x7b-qlora-gptq

GPTQ

2048 sequence length

VMware/open-instruct dataset

Training

axolotl was used for training on a 4x nvidia a100 gpu cluster.

the a100 GPU cluster has been graciously provided by lloorree.

trained on koishi commit 6e675d1 for one epoch

Base Model

rank 16 qlora tune of mistralai/Mixtral-8x7B-v0.1 (all modules, merged)

Prompting

The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: <|system|>, <|user|> and <|model|>.

The <|system|> prompt can be used to inject out-of-channel information behind the scenes, while the <|user|> prompt should be used to indicate user input. The <|model|> token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.