Hugging Face's logo

LoneStriker
/
Yi-34B-Spicyboros-3.1-2-LoRA

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Yi-34B-Spicyboros-3.1-2-LoRA / README.md
LoneStriker's picture
LoneStriker
Update README.md
bd1a130
preview code
|
raw
history blame contribute delete
1.63 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: airo-lora-out2
    results: []
datasets:
  - unalignment/spicy-3.1

Built with Axolotl

Fine-tune of Yi-34B with Spicyboros-3.1

Three epochs of fine tuning with @jondurbin's SpicyBoros-3.1 dataset. 4.65bpw should fit on a single 3090/4090, 5.0bpw, 6.0bpw, and 8.0bpw will require more than one GPU 24 GB VRAM GPU.

Please note: you may have to turn down repetition penalty to 1.0. The model seems to get into "thesaurus" mode sometimes without this change.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 6
  • eval_batch_size: 6
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 24
  • total_eval_batch_size: 12
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 3

Training results

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1