u-10bei/structured_data_with_cot_dataset
Viewer β’ Updated β’ 2.5k β’ 28
How to use makotonlo/LLM2026_DPO_SFT19_v12 with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-7b-instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "makotonlo/LLM2026_DPO_SFT19_v12")How to use makotonlo/LLM2026_DPO_SFT19_v12 with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for makotonlo/LLM2026_DPO_SFT19_v12 to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for makotonlo/LLM2026_DPO_SFT19_v12 to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for makotonlo/LLM2026_DPO_SFT19_v12 to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="makotonlo/LLM2026_DPO_SFT19_v12",
max_seq_length=2048,
)This model is a LoRA adapter evolved from the highly intelligent SFT model makotonlo/LLM2026_SFT_finalv19_7B. It has been fine-tuned using Direct Preference Optimization (DPO) to eliminate conversational chatter and enforce strict raw data output.
The primary objective of this version is to ensure the model outputs ONLY raw data (JSON, XML, YAML, CSV) without any preambles, markdown backticks (```), or explanations, to comply with strict competition rules.
When using this model, please use the same strict prompt template used during training to ensure the output starts directly with {, [, or <.