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

AstroHan
/
decision-head-qwen3.5-4b-rlcd-32k

Text Classification
PEFT
Safetensors
English
Chinese
lora
decision-model
typed-decisions
system-one
rlcd
Model card Files Files and versions
xet
Community

Instructions to use AstroHan/decision-head-qwen3.5-4b-rlcd-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use AstroHan/decision-head-qwen3.5-4b-rlcd-32k with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
    model = PeftModel.from_pretrained(base_model, "AstroHan/decision-head-qwen3.5-4b-rlcd-32k")
  • Notebooks
  • Google Colab
  • Kaggle
decision-head-qwen3.5-4b-rlcd-32k
20.1 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
AstroHan's picture
AstroHan
Correct the transfer table: per-seed values, released seed first
8349ce9 verified 14 days ago
  • .gitattributes
    1.52 kB
    initial commit 14 days ago
  • README.md
    8.75 kB
    Correct the transfer table: per-seed values, released seed first 14 days ago
  • adapter_config.json
    1.23 kB
    Release seed 1 adapter, model card, validation results and reference head 14 days ago
  • adapter_model.safetensors
    19.7 MB
    xet
    Release seed 1 adapter, model card, validation results and reference head 14 days ago
  • decision.py
    12.6 kB
    Release seed 1 adapter, model card, validation results and reference head 14 days ago
  • validation.json
    383 kB
    Release seed 1 adapter, model card, validation results and reference head 14 days ago