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

tianzl66
/
Qwen3-8B-MetaMathQA-50K-LoRA-Seed44

Text Generation
PEFT
Safetensors
lora
spectral-surgery
training-seed-replication
b300
math
seed-44
conversational
Model card Files Files and versions
xet
Community

Instructions to use tianzl66/Qwen3-8B-MetaMathQA-50K-LoRA-Seed44 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use tianzl66/Qwen3-8B-MetaMathQA-50K-LoRA-Seed44 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
    model = PeftModel.from_pretrained(base_model, "tianzl66/Qwen3-8B-MetaMathQA-50K-LoRA-Seed44")
  • Notebooks
  • Google Colab
  • Kaggle
Qwen3-8B-MetaMathQA-50K-LoRA-Seed44 / comparison
11 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
tianzl66's picture
tianzl66
Release audited B300 LoRA training seed 44; actual zero warmup and complete in-domain HNS results
36c201b verified 26 days ago
  • configuration_audit.md
    9.67 kB
    Release audited B300 LoRA training seed 44; actual zero warmup and complete in-domain HNS results 26 days ago
  • three_run_scores.json
    1.29 kB
    Release audited B300 LoRA training seed 44; actual zero warmup and complete in-domain HNS results 26 days ago