| | Fine-Tuning LLaVA (wandb.ai) |
| 3 points by byyoung3 on Feb 11, 2024 | past |
|
| | Diffusion Model from Scratch (wandb.ai) |
| 2 points by byyoung3 on Jan 5, 2024 | past |
|
| | Run Mistral 7B on M1 Mac (wandb.ai) |
| 111 points by byyoung3 on Dec 16, 2023 | past | 51 comments |
|
| | Neuron Hacking – Finetuning LLMs to act as key-value stores (wandb.ai) |
| 1 point by samshapley on Dec 3, 2023 | past | 1 comment |
|
| | Scaling Llama 2 to 32k Tokens With LongLora (wandb.ai) |
| 1 point by byyoung3 on Oct 31, 2023 | past |
|
| | Fine-Tuning Mistral7B on Python Code (wandb.ai) |
| 61 points by tarruda on Oct 8, 2023 | past | 11 comments |
|
| | Training Tiny Llamas for Fun–and Science (wandb.ai) |
| 3 points by sebg on Sept 14, 2023 | past |
|
| | Open Challenges for AI Research and Engineering with Chip Huyen (wandb.ai) |
| 1 point by byyoung3 on Aug 17, 2023 | past |
|
| | Forcing LLM's to repeat a word, but ban the word using logit bias (wandb.ai) |
| 5 points by samshapley on July 21, 2023 | past | 1 comment |
|
| | W&B Prompts (wandb.ai) |
| 1 point by haensi on April 22, 2023 | past | 1 comment |
|
| | W&B LLM Ops Tools (wandb.ai) |
| 2 points by ivstitia on April 21, 2023 | past |
|
| | A Recipe for Training Large Models using 2nd Order Methods (Distributed Shampoo) (wandb.ai) |
| 2 points by tim_sw on April 8, 2023 | past |
|
| | A Recipe for Training Large Models (wandb.ai) |
| 5 points by OnlineInference on April 8, 2023 | past |
|
| | Prompt Engineering LLMs with LangChain (wandb.ai) |
| 1 point by sonabinu on April 5, 2023 | past |
|
| | Prompt Engineering LLMs with LangChain and W&B (wandb.ai) |
| 3 points by babelfish on March 23, 2023 | past |
|
| | GPT-3.5 vs. GPT-4 Code Generation Comparison (wandb.ai) |
| 3 points by OnlineInference on March 19, 2023 | past |
|
| | Show HN: Track and Compare Audio Transcription with Whisper × W&B (wandb.ai) |
| 5 points by haensi on Feb 14, 2023 | past |
|
| | Stable Diffusion and the Samplers Mystery (wandb.ai) |
| 6 points by tosh on Dec 18, 2022 | past | 2 comments |
|
| | Can Apple’s M1 Help You Train Models Faster and Cheaper Than Nvidia’s V100? (wandb.ai) |
| 1 point by wslh on Dec 15, 2022 | past | 1 comment |
|
| | Speed Up Stable Diffusion on Your M1Pro MacBook Pro (wandb.ai) |
| 2 points by tosh on Dec 1, 2022 | past |
|
| | Galactica: 120B-Param Scientific Language Model by Papers with Code, Meta AI (wandb.ai) |
| 2 points by OnlineInference on Nov 15, 2022 | past |
|
| | Nvidia SC22: H100 and Quantum-2 Adoption; Omniverse and Library Updates (wandb.ai) |
| 1 point by OnlineInference on Nov 15, 2022 | past |
|
| | Google Cloud Next Keynote Recap: Translation Hub, Vertex AI Vision and More (wandb.ai) |
| 1 point by OnlineInference on Oct 11, 2022 | past |
|
| | AlphaTensor: DeepMind's AI for Efficient Matrix Multiplication Algorithms (wandb.ai) |
| 1 point by OnlineInference on Oct 6, 2022 | past |
|
| | The White House Office of Science and Tech Policy Reveals AI Bill of Rights (wandb.ai) |
| 2 points by OnlineInference on Oct 4, 2022 | past |
|
| | Make-a-Video: Meta AI's New Model for Text-to-Video Generation (wandb.ai) |
| 1 point by OnlineInference on Sept 29, 2022 | past | 1 comment |
|
| | Polyglot Releases Korean GPT Models (wandb.ai) |
| 1 point by OnlineInference on Sept 29, 2022 | past |
|
| | The Waitlist for DALL·E 2 Is Gone, Sign-Ups Now Open for Immediate Use (wandb.ai) |
| 1 point by OnlineInference on Sept 28, 2022 | past |
|
| | Harmonai's Dance Diffusion, MIT Licensed AI Audio Generation Tool (wandb.ai) |
| 4 points by knaik94 on Sept 28, 2022 | past |
|
| | BigCode: Hugging Face and ServiceNow Partner to Develop LLM for Code (wandb.ai) |
| 2 points by OnlineInference on Sept 27, 2022 | past |
|
|
| More |