RichardErkhov/CorticalStack_-_mistral-7b-tak-stack-dpo-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-7b-tak-stack-dpo - GGUF

• —Model creator: https://huggingface.co/CorticalStack/
• —Original model: https://huggingface.co/CorticalStack/mistral-7b-tak-stack-dpo/

Original model description: --- license: apache-2.0 tags:

• —dpo base_model:
• —mistralai/Mistral-7B-v0.1 dataset:
• —CorticalStack/tak-stack-dpo ---

mistral-7b-tak-stack-dpo

mistral-7b-tak-stack-dpo is a DPO fine-tuned version of mistralai/Mistral-7B-v0.1 using the CorticalStack/tak-stack-dpo dataset.

LoRA

• —r: 32
• —LoRA alpha: 32
• —LoRA dropout: 0.05

Training arguments

• —Batch size: 4
• —Gradient accumulation steps: 4
• —Optimizer: pagedadamw32bit
• —Max steps: 100
• —Learning rate: 5e-05
• —Learning rate scheduler type: cosine
• —Beta: 0.1
• —Max prompt length: 1024
• —Max length: 1536