How to use from
Unsloth StudioInstall 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 bunnycore/Llama-3.2-3B-Code-lora_model to start chattingUsing HuggingFace Spaces for Unsloth
# No setup required# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bunnycore/Llama-3.2-3B-Code-lora_model to start chattingLoad model with FastModel
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="bunnycore/Llama-3.2-3B-Code-lora_model",
max_seq_length=2048,
)Quick Links
Uploaded model
dataset = load_dataset("Crystalcareai/Code-feedback-sharegpt-renamed", split = "train")
dataset2 = load_dataset("MaziyarPanahi/Synthia-Coder-v1.5-I-sharegpt", split = "train")
dataset3 = load_dataset("Alignment-Lab-AI/CodeInterpreterData-sharegpt", split = "train")
dataset4 = load_dataset("adamo1139/m-a-p_CodeFeedback_norefusals_ShareGPT", split = "train")
dataset5 = load_dataset("mahiatlinux/Glaive-code-assistant-ShareGPT", split = "train")
dataset6 = load_dataset("Nitral-AI/Olympiad_Math-ShareGPT", split = "train")
- Developed by: bunnycore
- License: apache-2.0
- Finetuned from model : unsloth/llama-3.2-3b-instruct-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install Unsloth Studio (macOS, Linux, WSL)
# Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for bunnycore/Llama-3.2-3B-Code-lora_model to start chatting