mpasila/PIPPA-Named-7B-exl2-4bpw

This is an ExLlamaV2 quantized model in 4bpw of mpasila/PIPPA-Named-7B using the default calibration dataset.

Original Model card:

This is a merge of mpasila/PIPPA-Named-LoRA-7B.

LoRA trained in 4-bit with 8k context using alpindale/Mistral-7B-v0.2-hf as the base model for 1 epoch.

Dataset used is a modified version of KaraKaraWitch/PIPPA-ShareGPT-formatted.

Prompt format: ChatML

Uploaded model

• Developed by: mpasila
• License: apache-2.0
• Finetuned from model : unsloth/mistral-7b-v0.2-bnb-4bit

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.