jakebentley2001/

Mistral-Minitron-8B-Stage-1-merged

ARC Fine-tuned Qweun 7B (Merged) base_model: nvidia/Mistral-NeMo-Minitron-8B-Base 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/Mistral-Minitron-8B-Stage-1-merged") model = AutoModelForCausalLM.from_pretrained("jakebentley2001/Mistral-Minitron-8B-Stage-1-merged", torch_dtype="auto", device_map="auto")