Hugging Face's logo

LegalSign
/
Llama-3.1-Freego-8B-Instruct

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Llama-3.1-Freego-8B-Instruct / README.md
lianghsun's picture
lianghsun
Upload sft model started from Llama3.1-base with mapping table
4a28562
preview code
|
raw
history blame contribute delete
1.44 kB
metadata
library_name: transformers
license: other
base_model: meta-llama/Llama-3.1-8B
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: sft-2024-12-28-1
    results: []

sft-2024-12-28-1

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the patent-zh_tw-en-translation and the manythings-translations-alpaca datasets.

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: 5e-06
  • train_batch_size: 14
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 896
  • total_eval_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 30.0

Training results

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3