Instruction Fine-Tuning of Meta Llama 3.2-3B Instruct on Kannada Conversations. Tailoring the model to follow specific instructions in Kannada, enhancing its ability to generate relevant, context-aware responses based on conversational inputs. Using the Kannada Instruct dataset for fine-tuning! Happy Finetuning 🎋

training open-source meta gpu inference deployed production-ready quantization peft finetuning huggingface modular-code qlora bitsandbytes gguf 4bit-quantize unsloth 4bitprecision anthropic-hh-golden unified-language-model-aligning

• Updated Jan 30, 2025
• Jupyter Notebook

A simple custom QLoRA implementation for fine-tuning a language model (LLM) with basic tools such as PyTorch and Bitsandbytes, completely decoupled from Hugging Face.

llama fine-tuning custom-model llm qlora 4bit-quantize

• Updated Jan 29, 2024
• Python

Text Generation on Pre-Trained NousResearch’s Llama-2-7b-chat-hf using guanaco-llama2-1k dataset

text-generation pytorch huggingface llm llama2 4bit-quantize

• Updated Jul 28, 2024
• Jupyter Notebook

Sample project with combination of Whisper and Deepseek R1 for extracting key points from office meeting videos

ai transformers summarization speech-to-text lora quantization whisper dora finetuning llm whisper-ai 4bit-quantize unsloth deepseek-r1

• Updated Mar 6, 2025
• Jupyter Notebook