You can deploy this model and start earning money today!

SoominSion/
aire-llm-mistral7b-arc-final

Name: aire-llm-mistral7b-arc-final
Availability: InStock

peft

safetensors

mistralai/Mistral-7B-v0.1

adapter

Views

No views yet

SoominSion/aire-llm-mistral7b-arc-final

This repository contains the LoRA adapter for the final submitted checkpoint run10d_run9d_nearmiss_lr5e-6_beta0.03_e0.25.

Base Model

mistralai/Mistral-7B-v0.1
Local base revision used in experiments: 27d67f1b5f57dc0953326b2601d68371d40ea8da

Evaluation

Evaluation used EleutherAI lm-evaluation-harness on arc_challenge with 25 few-shot examples.

Metric	Value	Stderr
acc	0.6681	0.0138
acc_norm	0.7056	0.0133

These numbers are from the local saved checkpoint evaluation. A separate Hub reload evaluation should be run after upload to confirm reproducibility.

Training Summary

The model was trained with QLoRA using 4-bit NF4 quantization and fp16 compute. The training pipeline combined science-domain short-answer SFT, ARC label+answer-text realignment, and light eval-matched text-only DPO ranking correction.

Loading

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "mistralai/Mistral-7B-v0.1"
adapter = "SoominSion/aire-llm-mistral7b-arc-final"

tokenizer = AutoTokenizer.from_pretrained(adapter, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto")
model = PeftModel.from_pretrained(model, adapter)