Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

harshil30402
/
Cognius-mini-1B-v2

Text Generation
PEFT
Safetensors
lora
supervised-fine-tuning
reasoning
self-reflection
conversational
Model card Files Files and versions
xet
Community

Instructions to use harshil30402/Cognius-mini-1B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use harshil30402/Cognius-mini-1B-v2 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
    model = PeftModel.from_pretrained(base_model, "harshil30402/Cognius-mini-1B-v2")
  • Notebooks
  • Google Colab
  • Kaggle
Cognius-mini-1B-v2
2.21 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
harshil30402's picture
harshil30402
Add link to training/eval code repo
6ea3098 verified about 1 month ago
  • .gitattributes
    1.57 kB
    Upload 3 files over 1 year ago
  • README.md
    7.54 kB
    Add link to training/eval code repo about 1 month ago
  • adapter_config.json
    859 Bytes
    Upload model over 1 year ago
  • adapter_model.safetensors
    2.19 GB
    xet
    Upload model over 1 year ago
  • special_tokens_map.json
    435 Bytes
    Fix pad_token: correctly point to <|pad|> (id 128256) instead of <|eot_id|> about 1 month ago
  • tokenizer.json
    17.2 MB
    xet
    Upload 3 files over 1 year ago
  • tokenizer_config.json
    54.8 kB
    Fix pad_token: correctly point to <|pad|> (id 128256) instead of <|eot_id|> about 1 month ago