mistral_7b_sft_lora
This is a merged Mistral-7B model fine-tuned with a LoRA adapter for SFT or DPO tasks.
Base model: mistralai/Mistral-7B-v0.1
LoRA adapter: LoRA
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("meixiang123/mistral_7b_sft_lora")
tokenizer = AutoTokenizer.from_pretrained("meixiang123/mistral_7b_sft_lora")
- Downloads last month
- 78
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for meixiang123/mistral_7b_sft_lora
Base model
mistralai/Mistral-7B-v0.1