aletheap / ai_on_threads
☆38Updated last year
Related projects: ⓘ
- ☆89Updated 11 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- Highly commented implementations of Transformers in PyTorch☆126Updated last year
- ☆72Updated 3 months ago
- run paligemma in real time☆122Updated 4 months ago
- Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines☆195Updated 4 months ago
- A puzzle to learn about prompting☆106Updated last year
- Verbosity control for AI agents☆55Updated 3 months ago
- ☆48Updated 11 months ago
- An mlx project to train a base model on your whatsapp chats using (Q)Lora finetuning☆156Updated 8 months ago
- Simple Transformer in Jax☆100Updated 2 months ago
- Helpers and such for working with Lambda Cloud☆51Updated 10 months ago
- Functional local implementations of main model parallelism approaches☆93Updated last year
- A set of scripts and notebooks on LLM finetunning and dataset creation☆89Updated last week
- Drop in replacement for OpenAI, but with Open models.☆154Updated last year
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆93Updated 5 months ago
- Full finetuning of large language models without large memory requirements☆94Updated 8 months ago
- ☆141Updated last year
- ☆45Updated 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…☆143Updated this week
- GPT-2 (124M) quality in 5B tokens☆227Updated 2 weeks ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆42Updated last year
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆99Updated 8 months ago
- An automated tool for discovering insights from research papaer corpora☆131Updated 3 months ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆152Updated last year
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆217Updated 6 months ago
- run embeddings in MLX☆68Updated last month
- Cerule - A Tiny Mighty Vision Model☆67Updated 2 weeks ago
- ☆22Updated last year
- The history files when recording human interaction while solving ARC tasks☆91Updated this week