Developed by Jaeyeon Kang (CCK Solution)
Model Description
- This is a model for the korean language.
- We fine-tuned this model based on mistralai/Mixtral-8x7B-Instruct-v0.1 with our training dataset(private).
- SFT and DPO (LoRA) training are adjusted .
Run the model
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "JaeyeonKang/CCK-Gony_v3"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
text = "[INST] Put instruction here. [/INST]"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
