Mistral-7B-legal-cuad-lora-v1
Mistral-7B fine-tuned on Legal CUAD contract analysis QA. LoRA adapter (r=16, alpha=32). Identifies and analyzes 40+ contract clause types.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base, "MypodW23/Mistral-7B-legal-cuad-lora-v1")
tok = AutoTokenizer.from_pretrained("MypodW23/Mistral-7B-legal-cuad-lora-v1")
Training Details
- Base model: Mistral-7B-Instruct-v0.3
- Method: QLoRA (4-bit) + LoRA (r=16, alpha=32)
- Framework: unsloth + trl
- Hardware: Google Colab T4 (free tier)
- Part of: ModelForge LLMOps Platform
- Downloads last month
- 26
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for MypodW23/Mistral-7B-legal-cuad-lora-v1
Base model
mistralai/Mistral-7B-v0.3 Finetuned
mistralai/Mistral-7B-Instruct-v0.3