metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - mistral
  - trl
base_model: unsloth/mistral-7b-bnb-4bit

Uploaded model

Developed by: priamai
License: apache-2.0
Finetuned from model : unsloth/mistral-7b-bnb-4bit

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

Num GPUs = 1

Num Epochs = 2

Batch size per device = 2

Gradient Accumulation steps = 2

Total batch size = 8

otal steps = 2

Number of trainable parameters = 41,943,040

Total Samples = 800

Source of reports: ORKL