Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Nyingi101
/
math-tutor-tinyllama-lora

Text Generation
PEFT
Safetensors
English
French
Kinyarwanda
lora
qlora
education
math
multilingual
children
kinyarwanda
french
english
numeracy
adaptive-learning
conversational
Eval Results (legacy)
Model card Files Files and versions
xet
Community

Instructions to use Nyingi101/math-tutor-tinyllama-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use Nyingi101/math-tutor-tinyllama-lora with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
    model = PeftModel.from_pretrained(base_model, "Nyingi101/math-tutor-tinyllama-lora")
  • Notebooks
  • Google Colab
  • Kaggle
math-tutor-tinyllama-lora
10.9 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
Nyingi101's picture
Nyingi101
Add model card with training details, usage examples, and multilingual docs
e82f393 verified 20 days ago
  • .gitattributes
    1.52 kB
    initial commit 20 days ago
  • README.md
    4.86 kB
    Add model card with training details, usage examples, and multilingual docs 20 days ago
  • adapter_config.json
    687 Bytes
    Add production TinyLlama QLoRA adapter β€” train_loss=0.477, 3 epochs, 2000 EN/FR/KIN pairs 20 days ago
  • adapter_model.safetensors
    9.03 MB
    xet
    Add production TinyLlama QLoRA adapter β€” train_loss=0.477, 3 epochs, 2000 EN/FR/KIN pairs 20 days ago
  • special_tokens_map.json
    437 Bytes
    Add production TinyLlama QLoRA adapter β€” train_loss=0.477, 3 epochs, 2000 EN/FR/KIN pairs 20 days ago
  • tokenizer.json
    1.84 MB
    Add production TinyLlama QLoRA adapter β€” train_loss=0.477, 3 epochs, 2000 EN/FR/KIN pairs 20 days ago
  • tokenizer_config.json
    1.34 kB
    Add production TinyLlama QLoRA adapter β€” train_loss=0.477, 3 epochs, 2000 EN/FR/KIN pairs 20 days ago