awesome-ChatGPT-repositories
Section: Others · 【大模型】3小时完全从0训练一个仅有26M的小参数GPT,最低仅需2G显卡即可推理训练!
Entry
Appears in 4 awesome lists
Train a 64M-parameter LLM from scratch in just 2 hours for $3. Complete from-scratch implementation covering MoE, data cleaning, pretraining, SFT, LoRA, RLHF (DPO/PPO/GRPO), tool use, and model distillation. All core algorithms implemented in pure PyTorch without high-level abstractions.…
Section: Others · 【大模型】3小时完全从0训练一个仅有26M的小参数GPT,最低仅需2G显卡即可推理训练!
Section: 小语言模型 Small Language Model
Section: 7. Training & Fine-tuning Ecosystem · Train a 64M-parameter LLM from scratch in just 2 hours for $3. Complete from-scratch implementation covering MoE, data cleaning, pretraining, SFT, LoRA, RLHF (DPO/PPO/GRPO), tool use, and model distillation. All core algorithms implemented in pure PyTorch without high-level abstractions.…
Section: Other · 🧠 Train a 64M-parameter LLM from scratch in just 2h!
(from Hpcaitech) - A Unified Deep Learning System for Large-Scale Parallel Training (1D, 2D, 2.5D, 3D and sequence parallelism, and ZeRO protocol).
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library. ray.io
Open platform for training, serving, and evaluating large language model chatbots. Powers Chatbot Arena (lmarena.ai) serving 10M+ requests for 70+ LLMs. Includes training code for Vicuna, MT-Bench evaluation, and distributed multi-model serving with OpenAI-compatible APIs. Apache 2.0 licensed.
Whisper is a general-purpose speech recognition model that can be run locally offline. It can transcribe audio from and to multiple languages.
GPT Researcher is an AI-powered autonomous agent designed for efficient and unbiased online research, generating detailed reports by leveraging recent advancements in AI and web scraping, with a focus on speed, reliability, and cost-effectiveness github | github profile