Instructions to use NayanPal/truthtriage-llama2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NayanPal/truthtriage-llama2-7b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-2-7b-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "NayanPal/truthtriage-llama2-7b")

Transformers

How to use NayanPal/truthtriage-llama2-7b with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NayanPal/truthtriage-llama2-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

Unsloth Studio

How to use NayanPal/truthtriage-llama2-7b 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 NayanPal/truthtriage-llama2-7b 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 NayanPal/truthtriage-llama2-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NayanPal/truthtriage-llama2-7b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="NayanPal/truthtriage-llama2-7b",
    max_seq_length=2048,
)

truthtriage-llama2-7b / tokenizer.model

Commit History

Upload folder using huggingface_hub

4473a2f
verified

NayanPal commited on Feb 27

Commit History

Upload folder using huggingface_hub 4473a2f verified

Upload folder using huggingface_hub

4473a2f
verified