Search: github.com/ftrain | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

241.

PyTorch 1.7 Released with CUDA 11, New APIs for FFTs, Win Distributed Training (github.com/pytorch)

29 points

6 years ago

242.

Show HN: Stable Diffusion training, inpainting, classifier guidance and upscale (github.com/Jack000)

29 points

4 years ago

243.

Hierarchical Reasoning Model – 1k training samples SoTA reasoning v/s CoT (github.com/sapientinc)

26 points

10 months ago

244.

Show HN: MyGPT a toy LLM which can be trained on Project Gutenberg and dad jokes (github.com/jhud)

25 points

3 years ago

245.

DeepSpeed Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-Like Models (github.com/microsoft)

25 points

3 years ago

246.

OpenSora Releases its first trained checkpoints (2-5 SEC, 512x512 T2V) (github.com/hpcaitech)

24 points

2 years ago

247.

RustTraining: Beginner, advanced, expert level Rust training material (github.com/microsoft)

24 points

2 months ago

248.

Show HN: I Trained a 2D Game Animation Generation Model(Fully Open-Source) (github.com/lyogavin)

23 points

2 years ago

249.

Show HN: Per-instance TSP Solver with No Pre-training (1.66% gap on d1291)

21 points

5 months ago

250.

Composer: A new PyTorch library to train models 4x faster with better algorithms (github.com/mosaicml)

21 points

4 years ago

251.

A snake game controlled by neural network and trained by genetic algorithm (github.com/mraythree)

19 points

10 years ago

252.

Show HN: Autodistill – Use big slow foundation models to train small fast models (github.com/autodistill)

18 points

3 years ago

253.

Tune PaLM 2 with your own RLHF training data (github.com/GoogleCloudPlatform)

17 points

3 years ago

254.

RBM trained with persistent states, written from scratch in Julia (github.com/jostmey)

17 points

10 years ago

255.

Show HN: Graphsignal – ML profiler to speed up training and inference (github.com/graphsignal)

16 points

4 years ago

256.

RDMA-Powered Distributed Cache for Fast AI Training and Inference (github.com/blackbird-io)

16 points

9 months ago

257.

Show HN: Script to download Tweets into a format ideal for training an AI model (github.com/minimaxir)

16 points

6 years ago

258.

Show HN: RAGatouille, a simple lib to use&train top retrieval models in RAG apps (github.com/bclavie)

15 points

2 years ago

259.

Liger-Kernel: Efficient Triton kernels for LLM training (github.com/linkedin)

15 points

2 years ago

260.

Ask HN: Are you training and running custom LLMs and how are you doing it?

15 points

3 years ago

261.

Show HN: Beating Hinton et al.'s capsule net with fewer params and less training

14 points

7 years ago

262.

Show HN: I trained a chess engine to play like humans

14 points

a month ago

263.

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. (github.com/datadreamer-dev)

14 points

2 years ago

264.

A LLM trained only on data from certain time periods to reduce modern bias (github.com/haykgrigo3)

13 points

6 months ago

265.

Show HN: An RDMA/Infiniband Distributed Cache for Fast Inference and Training (github.com/blackbird-io)

13 points

9 months ago

266.

SagemakerDebugger – Tool to peek inside deep learning/xgboost models training (github.com/awslabs)

13 points

6 years ago

267.

Scalable Pre-Training of Large Autoregressive Image Models (Aim by Apple) (github.com/apple)

12 points

2 years ago

268.

Open Source Historical LLM trained exclusively on 19th century text (github.com/haykgrigo3)

12 points

6 months ago

269.

Yandex Unveils YaFSDP for 26% Faster LLM Training (github.com/yandex)

12 points

2 years ago

270.

ML: Most powerful free annotation tool yet for TrainingData

12 points

7 years ago