Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

taba0207
/
qwen3-4b-sft-dpo-structeval

Text Generation
PEFT
Safetensors
English
dpo
unsloth
qwen
alignment
conversational
Model card Files Files and versions
xet
Community

Instructions to use taba0207/qwen3-4b-sft-dpo-structeval with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use taba0207/qwen3-4b-sft-dpo-structeval with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit")
    model = PeftModel.from_pretrained(base_model, "taba0207/qwen3-4b-sft-dpo-structeval")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • Unsloth Studio

    How to use taba0207/qwen3-4b-sft-dpo-structeval 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 taba0207/qwen3-4b-sft-dpo-structeval 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 taba0207/qwen3-4b-sft-dpo-structeval to start chatting
    Using HuggingFace Spaces for Unsloth
    # No setup required
    # Open https://huggingface.co/spaces/unsloth/studio in your browser
    # Search for taba0207/qwen3-4b-sft-dpo-structeval to start chatting
    Load model with FastModel
    pip install unsloth
    from unsloth import FastModel
    model, tokenizer = FastModel.from_pretrained(
        model_name="taba0207/qwen3-4b-sft-dpo-structeval",
        max_seq_length=2048,
    )
qwen3-4b-sft-dpo-structeval
280 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
taba0207's picture
taba0207
Update README.md
4e936af verified 4 months ago
  • .gitattributes
    1.57 kB
    Upload folder using huggingface_hub 4 months ago
  • README.md
    1.97 kB
    Update README.md 4 months ago
  • adapter_config.json
    887 Bytes
    Upload folder using huggingface_hub 4 months ago
  • adapter_model.safetensors
    264 MB
    xet
    Upload folder using huggingface_hub 4 months ago
  • added_tokens.json
    707 Bytes
    Upload folder using huggingface_hub 4 months ago
  • chat_template.jinja
    2.51 kB
    Upload folder using huggingface_hub 4 months ago
  • merges.txt
    1.67 MB
    Upload folder using huggingface_hub 4 months ago
  • special_tokens_map.json
    614 Bytes
    Upload folder using huggingface_hub 4 months ago
  • tokenizer.json
    11.4 MB
    xet
    Upload folder using huggingface_hub 4 months ago
  • tokenizer_config.json
    5.43 kB
    Upload folder using huggingface_hub 4 months ago
  • training_args.bin
    6.8 kB
    xet
    Upload folder using huggingface_hub 4 months ago
  • vocab.json
    2.78 MB
    Upload folder using huggingface_hub 4 months ago