ProjectZ Experiments
Collection
Models trained while at eGain • 21 items • Updated
How to use chreh/math-lora-llama-3-8B with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("chreh/math-lora-llama-3-8B", dtype="auto")How to use chreh/math-lora-llama-3-8B with Unsloth Studio:
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 chreh/math-lora-llama-3-8B to start chatting
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 chreh/math-lora-llama-3-8B to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for chreh/math-lora-llama-3-8B to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="chreh/math-lora-llama-3-8B",
max_seq_length=2048,
)This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Base model
unsloth/llama-3-8b-Instruct-bnb-4bit