Wannaphong Phatthiyaphaibun's repositories
fixthaipdf
Fix Thai PDF
datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
deep_4_all
Courses a codes that I use to teach deeplearing
EasyLM
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
EfficientWord-Net
OneShot Learning-based hotword detection.
gigaGPT
a small code base for training large models
huggingface_hub
The official Python client for the Huggingface Hub.
lightning-GPT
Train and run GPTs with Lightning
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
llama3
The official Meta Llama 3 GitHub site
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
mistral-src
Reference implementation of Mistral AI 7B v0.1 model.
New-Day-Countdown
New Day Countdown
sacrebleu
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
state-of-open-source-ai
:closed_book: Clarity in the current fast-paced mess of Open Source innovation
th
Thai website - PyThaiNLP
thai_sentiment
The (extremely) naive sentiment classification function based on NBSVM trained on wisesight_sentiment
TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
TPU-Alignment
Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free
TUD
Thai Universal Dependency Treebank