Llama-3-8B Fine-tuned for Financial QA
Ce modèle est une version fine-tunée de Meta-Llama-3-8B-Instruct utilisant LoRA sur le dataset virattt/financial-qa-10K.
Utilisation
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "nribal/llama3-financial-qa")
tokenizer = AutoTokenizer.from_pretrained("NousResearch/Meta-Llama-3-8B-Instruct")
Dataset
- Dataset: virattt/financial-qa-10K
- Configuration: LoRA r=8, alpha=16
- Format: Question/Answer pairs
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nribal/llama3-financial-qa
Base model
NousResearch/Meta-Llama-3-8B-Instruct