Edit model card

Developed by Jaeyeon Kang (CCK Solution)

Model Description

  • This is a model for the korean language.
  • We fine-tuned this model based on 152334H/miqu-1-70b-sf with our training dataset(private).
  • SFT and DPO (QLoRA) training are adjusted .

Run the model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "JaeyeonKang/CCK-Asura-v1"
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))
Downloads last month
Model size
69B params
Tensor type