Isaak Carter Augustus
Update README.md
1aba652 verified
|
raw
history blame
No virus
654 Bytes
metadata
base_model: unsloth/llama-3-8b-bnb-4bit
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft

Still in Beta!!!

Uploaded model

  • Developed by: Isaak-Carter
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-8b-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

  "per_device_train_batch_size": 2,
  "gradient_accumulation_steps": 8,
  "max_steps": 100,
  "learning_rate": 2e-4,
  "optim": "adamw_8bit",
  "weight_decay": 0.01,
  "lr_scheduler_type": "cosine"