tysam-code / hlb-gptLinks
Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to larger models with one parameter change (feature currently in alpha).
☆345Updated 10 months ago
Alternatives and similar repositories for hlb-gpt
Users that are interested in hlb-gpt are comparing it to the libraries listed below
Sorting:
- a small code base for training large models☆299Updated last month
- ☆92Updated last year
- Puzzles for exploring transformers☆347Updated 2 years ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆205Updated 6 months ago
- ☆143Updated 2 years ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆581Updated 10 months ago
- Simple Transformer in Jax☆137Updated 11 months ago
- An interactive exploration of Transformer programming.☆264Updated last year
- Helpers and such for working with Lambda Cloud☆51Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆230Updated 7 months ago
- Language Modeling with the H3 State Space Model☆518Updated last year
- ☆301Updated 11 months ago
- A puzzle to learn about prompting☆127Updated 2 years ago
- JAX implementation of the Llama 2 model☆217Updated last year
- ☆267Updated 10 months ago
- Fast bare-bones BPE for modern tokenizer training☆156Updated 2 months ago
- ☆412Updated last year
- Open weights language model from Google DeepMind, based on Griffin.☆639Updated last week
- Extract full next-token probabilities via language model APIs☆248Updated last year
- A really tiny autograd engine☆95Updated last week
- seqax = sequence modeling + JAX☆155Updated last month
- ☆431Updated 7 months ago
- The repository for the code of the UltraFastBERT paper☆514Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆711Updated last year
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆171Updated this week
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆584Updated this week
- Solve puzzles. Learn CUDA.☆64Updated last year
- Full finetuning of large language models without large memory requirements☆93Updated last year
- Inference code for Persimmon-8B☆415Updated last year