Instructions to use fay-ong/new-llamafactory-llama-3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use fay-ong/new-llamafactory-llama-3-8b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "fay-ong/new-llamafactory-llama-3-8b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use fay-ong/new-llamafactory-llama-3-8b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for fay-ong/new-llamafactory-llama-3-8b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for fay-ong/new-llamafactory-llama-3-8b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for fay-ong/new-llamafactory-llama-3-8b to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="fay-ong/new-llamafactory-llama-3-8b", max_seq_length=2048, )
| {"current_steps": 10, "total_steps": 62, "loss": 0.2613, "learning_rate": 1.9853538358476933e-05, "epoch": 0.16, "percentage": 16.13, "elapsed_time": "0:02:24", "remaining_time": "0:12:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 62, "loss": 0.216, "learning_rate": 1.736741137876405e-05, "epoch": 0.32, "percentage": 32.26, "elapsed_time": "0:04:49", "remaining_time": "0:10:07", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 62, "loss": 0.1431, "learning_rate": 1.2542183341934873e-05, "epoch": 0.48, "percentage": 48.39, "elapsed_time": "0:07:13", "remaining_time": "0:07:42", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 62, "loss": 0.088, "learning_rate": 6.909830056250527e-06, "epoch": 0.64, "percentage": 64.52, "elapsed_time": "0:09:36", "remaining_time": "0:05:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 62, "loss": 0.107, "learning_rate": 2.2585838936091753e-06, "epoch": 0.8, "percentage": 80.65, "elapsed_time": "0:11:59", "remaining_time": "0:02:52", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 62, "loss": 0.118, "learning_rate": 6.51826465144978e-08, "epoch": 0.96, "percentage": 96.77, "elapsed_time": "0:14:24", "remaining_time": "0:00:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 62, "total_steps": 62, "epoch": 0.992, "percentage": 100.0, "elapsed_time": "0:14:52", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} | |