jakebentley2001/

arc-mistral-8b-merged

ARC Fine-tuned Llama 3.2 3B (Merged) base_model: chuanli11/Llama-3.2-3B-Instruct-uncensored pipeline_tag: text-generation tags:

merged-weights

causal-lm

arc

This repo contains the merged weights (base + LoRA fused).

Usage python Copy code from transformers import AutoTokenizer, AutoModelForCausalLM tok = AutoTokenizer.from_pretrained("jakebentley2001/arc-llama3-3b-merged") model = AutoModelForCausalLM.from_pretrained("jakebentley2001/arc-llama3-3b-merged", torch_dtype="auto", device_map="auto")