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

Werea-co
/
Werea-LLM-3B

Text Generation
PEFT
Safetensors
Turkish
turkish
instruction-tuned
qlora
chat
werea
conversational
Model card Files Files and versions
xet
Community

Instructions to use Werea-co/Werea-LLM-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use Werea-co/Werea-LLM-3B with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
    model = PeftModel.from_pretrained(base_model, "Werea-co/Werea-LLM-3B")
  • Notebooks
  • Google Colab
  • Kaggle
Werea-LLM-3B
131 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
GoktugD's picture
GoktugD
Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered)
4d5992a verified about 2 months ago
  • .gitattributes
    1.57 kB
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • README.md
    2.77 kB
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • adapter_config.json
    1.16 kB
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • adapter_model.safetensors
    120 MB
    xet
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • chat_template.jinja
    2.51 kB
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • tokenizer.json
    11.4 MB
    xet
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • tokenizer_config.json
    694 Bytes
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago
  • train-manifest.json
    168 Bytes
    Werea-LLM-3B: Turkish QLoRA SFT on Qwen2.5-3B-Instruct (80K quality-filtered) about 2 months ago