Instructions to use makotonlo/LLM2026_DPO_SFT19_v11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use makotonlo/LLM2026_DPO_SFT19_v11 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_v11") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use makotonlo/LLM2026_DPO_SFT19_v11 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
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_v11 to start chatting
Install Unsloth Studio (Windows)
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_v11 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for makotonlo/LLM2026_DPO_SFT19_v11 to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="makotonlo/LLM2026_DPO_SFT19_v11", max_seq_length=2048, )
LLM2026_DPO_SFT19_v11
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.
π― Optimization Goal (Strict No-Preamble)
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.
π Training Configuration
- Base Intelligence: makotonlo/LLM2026_SFT_finalv19_7B (v19)
- Method: DPO (Direct Preference Optimization)
- Learning Rate: 5e-06 (Low LR to preserve structured logic)
- Beta: 0.1 (Strong penalty for conversational responses)
- Max Steps: 500
- LoRA Config: r=64, alpha=64
β οΈ Important: Usage Note
When using this model, please use the same strict prompt template used during training to ensure the output starts directly with {, [, or <.
Framework versions
- PEFT 0.13.2
- Downloads last month
- 1