metadata

license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: TheBloke/zephyr-7B-beta-GPTQ
model-index:
  - name: zephyr-med
    results: []

zephyr-med

This model is a fine-tuned version of TheBloke/zephyr-7B-beta-GPTQ on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

quant_method: gptq
bits: 4
tokenizer: None
dataset: None
group_size: 128
damp_percent: 0.1
desc_act: True
sym: True
true_sequential: True
use_cuda_fp16: False
model_seqlen: 4096
block_name_to_quantize: model.layers
module_name_preceding_first_block: ['model.embed_tokens']
batch_size: 1
pad_token_id: None
use_exllama: False
max_input_length: None
exllama_config: {'version': <ExllamaVersion.ONE: 1>}
cache_block_outputs: True

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 250
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.7.0
Transformers 4.36.0
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0