Hugging Face's logo

ShirinYamani
/
mistral7b-fine-tuned-qlora

Text Generation
PEFT
TensorBoard
Safetensors
English
PEFT
Qlora
mistral-7b
fine-tuning
Model card Files Metrics Community
mistral7b-fine-tuned-qlora / README.md
ShirinYamani's picture
ShirinYamani
Update README.md
d4d2996 verified
preview code
|
raw
history blame
1.64 kB
metadata
license: mit
library_name: peft
tags:
  - PEFT
  - Qlora
  - mistral-7b
  - fine-tuning
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: mistral7b-fine-tuned-qlora
    results: []
datasets:
  - timdettmers/openassistant-guanaco
pipeline_tag: text-generation
language:
  - en
im

mistral7b-fine-tuned-qlora

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on timdettmers/openassistant-guanaco dataset.

Usage guidance

Please refer to this notebook for a complete demo including notes regarding cloud deployment

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • training_steps: 10
  • mixed_precision_training: Native AMP

Framework versions

  • PEFT 0.11.2.dev0
  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1