Downloads · 30 days
0
Llama-3-8B-DPO-orca-NEFTune
Technonia/Llama-3-8B-DPO-orca-NEFTune
Llama-3-8B-DPO-orca-NEFTune is a machine learning model from Technonia. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Finetune Llama-3-8B model with Orca-DPO dataset.
Access
Public
Updated Apr 30, 2024
Repo size
336 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors336 MB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024
- SHA
- 86c51cc1
Model card
From the Hugging Face model README
Model Card for Model ID
Model Details
Finetune Llama-3-8B model with Orca-DPO dataset.
Training Details
Training Data
Trained on Orca dataset (DPO).
Training Procedure
Add NEFTune module for robustness, and fine-tune the model with DPO trainer.
Training Hyperparameters
- lora_alpha = 16
- lora_r = 64
- lora_dropout = 0.1
- adam_beta1 = 0.9
- adam_beta2 = 0.999
- weight_decay = 0.001
- max_grad_norm = 0.3
- learning_rate = 2e-4
- bnb_4bit_quant_type = nf4
- optim = "paged_adamw_32bit"
- optimizer_type = "paged_adamw_32bit"
- max_steps = 5000
- gradient_accumulation_steps = 4
- Library
- transformers
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024