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).
☆348Updated last year
Alternatives and similar repositories for hlb-gpt
Users that are interested in hlb-gpt are comparing it to the libraries listed below
Sorting:
- Fast bare-bones BPE for modern tokenizer training☆165Updated 3 months ago
- ☆94Updated 2 years ago
- Ungreedy subword tokenizer and vocabulary trainer for Python, Go & Javascript☆601Updated last year
- Helpers and such for working with Lambda Cloud☆51Updated last year
- ☆416Updated last year
- ☆309Updated last year
- Puzzles for exploring transformers☆371Updated 2 years ago
- The repository for the code of the UltraFastBERT paper☆519Updated last year
- Language Modeling with the H3 State Space Model☆518Updated 2 years ago
- Simple Transformer in Jax☆139Updated last year
- ☆144Updated 2 years ago
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆293Updated last year
- JAX implementation of the Llama 2 model☆218Updated last year
- Extract full next-token probabilities via language model APIs☆248Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆717Updated last year
- A puzzle to learn about prompting☆135Updated 2 years ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆232Updated 11 months ago
- Inference code for Persimmon-8B☆414Updated 2 years ago
- a small code base for training large models☆310Updated 5 months ago
- batched loras☆346Updated 2 years ago
- git extension for {collaborative, communal, continual} model development☆216Updated 10 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆652Updated 4 months ago
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day☆257Updated last year
- ☆281Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆667Updated this week
- Accelerate, Optimize performance with streamlined training and serving options with JAX.☆311Updated this week
- A repository for log-time feedforward networks