koishi-8x7b-qlora / README.md
ewof's picture
Create README.md
58323a0
|
raw
history blame
947 Bytes
---
datasets:
- ewof/koishi-instruct-metharme
---
## Training
[axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
on a 4x nvidia a100 gpu cluster.
the a100 GPU cluster has been graciously provided by [lloorree](https://huggingface.co/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.