Search: github.com/tpai | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

571.

Understanding R1-Zero-Like Training: A Critical Perspective (github.com/sail-sg)

160 points

a year ago

572.

Forth implemented in Rust trait system (github.com/Ashymad)

157 points

6 years ago

573.

Train CIFAR10 to 94% in under 10 seconds on a single A100 (github.com/tysam-code)

151 points

3 years ago

574.

Show HN: Streamdal – an open-source tail -f for your data (github.com/streamdal)

148 points

3 years ago

575.

Paper Tape Is All You Need – Training a Transformer on a 1976 Minicomputer (github.com/dbrll)

145 points

2 months ago

576.

Extreme video compression with prediction using pre-trainded diffusion models (github.com/ElesionKyrie)

144 points

2 years ago

577.

01-AI/Yi: A series of large language models trained from scratch (github.com/01-ai)

143 points

3 years ago

578.

Open-Llama: Complete training pipeline for building large language models (github.com/s-JoL)

141 points

3 years ago

579.

Ask HN: Has Anyone Trained a personal LLM using their personal notes?

138 points

2 years ago

580.

Using OpenAI Gym to train an open-source 3D printed robot (github.com/nicrusso7)

135 points

6 years ago

581.

Diffusion training from scratch on a micro-budget (github.com/SonyResearch)

135 points

a year ago

582.

YaFSDP: a sharded data parallelism framework, faster for pre-training LLMs (github.com/yandex)

135 points

2 years ago

583.

Schedule-Free Learning – A New Way to Train (github.com/facebookresearch)

131 points

2 years ago

584.

TScale – Distributed training on consumer GPUs (github.com/Foreseerr)

130 points

a year ago

585.

TensorFlow Code for Google Research's BERT: Pre-Training Method for NLP Tasks (github.com/google-research)

129 points

8 years ago

586.

Show HN: Set of trained deep learning models for computer vision (github.com/fchollet)

127 points

10 years ago

587.

Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL (github.com/Danau5tin)

125 points

10 months ago

588.

Show HN: Python decorator that enables arbitrarily-deep tail/non-tail recursion (github.com/tylerhou)

119 points

4 years ago

589.

Tail-call optimization added to 6to5 compiler (github.com/6to5)

117 points

11 years ago

590.

Training open-source LLMs on ChatGPT output is a really bad idea. (gist.github.com)

114 points

3 years ago

591.

NanoGPT: The simplest, fastest repository for training medium-sized GPTs (github.com/karpathy)

114 points

2 years ago

592.

How to Train and Build a Conversational News Chatbot (github.com/tzano)

108 points

8 years ago

593.

List of European train stations and associated metadata (github.com/capitainetrain)

107 points

thibaut_barrere

11 years ago

594.

Show HN: Ts-SSH – SSH over Tailscale without running the daemon (github.com/derekg)

103 points

a year ago

595.

Driving dataset for car autopilot AI training (github.com/commaai)

100 points

10 years ago

596.

Horovod: Distributed Training Framework for TensorFlow, Keras, and PyTorch (github.com/uber)

100 points

8 years ago

597.

Agent Lightning: Train agents with RL (no code changes needed) (github.com/microsoft)

98 points

7 months ago

598.

Show HN: Tacopy – Tail Call Optimization for Python (github.com/raaidrt)

95 points

6 months ago

599.

Show HN: less than 650 LOC trainable GPT only using NumPy (github.com/joennlae)

90 points

3 years ago

600.

Show HN: Wanderer – an open-source trail database (github.com/Flomp)

89 points

2 years ago