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

cmndcntrlcyber
/
qwen14b-code-trainer-v8_mixed

Text Generation
PEFT
Safetensors
code-generation
tool-calling
lora
qwen2.5-coder
code-trainer
agentic
conversational
Model card Files Files and versions
xet
Community

Instructions to use cmndcntrlcyber/qwen14b-code-trainer-v8_mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use cmndcntrlcyber/qwen14b-code-trainer-v8_mixed with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-14B-Instruct")
    model = PeftModel.from_pretrained(base_model, "cmndcntrlcyber/qwen14b-code-trainer-v8_mixed")
  • Notebooks
  • Google Colab
  • Kaggle
qwen14b-code-trainer-v8_mixed
562 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 12 commits
cmndcntrlcyber's picture
cmndcntrlcyber
Sync model card from docs/model_cards/qwen14b-code-trainer-v8_mixed.md
838b54f verified 1 day ago
  • .gitattributes
    1.57 kB
    Phase 4A v8_mixed sweep β€” eval_loss=0.4584397077560425 8 days ago
  • README.md
    6.41 kB
    Sync model card from docs/model_cards/qwen14b-code-trainer-v8_mixed.md 1 day ago
  • adapter_config.json
    1.11 kB
    Phase 4A v8_mixed sweep β€” eval_loss=0.4837215840816498 7 days ago
  • adapter_model.safetensors
    551 MB
    xet
    Phase 4A v8_mixed sweep β€” eval_loss=0.4837215840816498 7 days ago
  • chat_template.jinja
    2.51 kB
    Phase 4A v8_mixed sweep β€” eval_loss=0.4584397077560425 8 days ago
  • phase4-agent-eval.json
    2 kB
    V7 agent eval (nexus-aligned): 5/5 making progress 7 days ago
  • phase4-benchmark-gsm8k-v7.json
    611 Bytes
    Phase 4 benchmark: gsm8k (0-shot) 7 days ago
  • phase4-eval-v7.json
    424 Bytes
    Phase 4 eval-only: phase4-eval-v7.json 7 days ago
  • phase4-result.json
    506 Bytes
    Phase 4A v8_mixed sweep β€” eval_loss=0.4837215840816498 7 days ago
  • phase4-tool-call-eval.json
    4.26 kB
    V7 tool-calling eval (nexus-aligned): 6/10 (60%) 7 days ago
  • tokenizer.json
    11.4 MB
    xet
    Phase 4A v8_mixed sweep β€” eval_loss=0.4584397077560425 8 days ago
  • tokenizer_config.json
    693 Bytes
    Phase 4A v8_mixed sweep β€” eval_loss=0.4584397077560425 8 days ago