Llama 3.3 70B LoRA โ Numeric Claim Verifier
LoRA adapter trained with Adaption AutoScientist on the Numeric Claim Verifier science dataset.
Results
| Field | Value |
|---|---|
| Base model | meta-llama/Llama-3.3-70B-Instruct-Reference |
| Best win rate | 64.51% |
| Run ID | b6bf9b12-1f71-4571-bba0-2cf5ad215b2c |
| Dataset ID | 8b2324dc-2fab-4992-9bde-8c246516d737 |
| Training type | LoRA (r=8, ฮฑ=8, q_proj+v_proj) |
Task
Classify scientific/statistical numeric claims as:
correct | wrong_direction | wrong_magnitude | unverifiable
Files
PEFT adapter (adapter_model.safetensors, adapter_config.json) + tokenizer files from the AutoScientist checkpoint.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "meta-llama/Llama-3.3-70B-Instruct"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, "REPO_ID_HERE")
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for mishface123/llama-3.3-70b-numeric-claim-verifier-lora
Base model
meta-llama/Llama-3.1-70B Finetuned
meta-llama/Llama-3.3-70B-Instruct