Hackernews posts about RedPajama

  1. New Dataset: RedPajama Dynamic Topic Modeling, 100K Docs W Topic Heirarchies (huggingface.co)
    5 points by IEatPrompts 12 days ago | discuss
  2. RedPajama: Reproduction of LLaMA with friendly license (www.together.xyz)
    864 points by tim_sw over 1 year ago | 216 comments
  3. Releasing 3B and 7B RedPajama (www.together.xyz)
    363 points by antimatter15 over 1 year ago | 106 comments
  4. RedPajama v2 Open Dataset with 30T Tokens for Training LLMs (together.ai)
    236 points by programd about 1 year ago | 60 comments
  5. RedPajama 7B (an Apache 2.0-licensed LLaMa) is now available (www.together.xyz)
    85 points by bestcoder69 over 1 year ago | 25 comments
  6. SlimPajama: A 627B token cleaned and deduplicated version of RedPajama (www.cerebras.net)
    60 points by andyk over 1 year ago | 7 comments
  7. Running RedPajama and other open LLMs on phones, browsers and AMD/NV/Intel GPUs (mlc.ai)
    11 points by junrushao1994 over 1 year ago | discuss
  8. RedPajama-Incite-7B-Instruct Outperforms LLaMA on MMLU (twitter.com)
    9 points by vipulved over 1 year ago | 1 comments
  9. RedPajama at 440B tokens higher quality than Pythia and StableLM (www.together.xyz)
    6 points by jamiedg over 1 year ago | 2 comments
  10. RedPajama-Data-v2: 30T tokens filtered and de-duplicated (twitter.com)
    4 points by leumassuehtam about 1 year ago | discuss
  11. Mlc-Chat – RedPajama-Incite-Chat-3B on macOS (til.simonwillison.net)
    4 points by swyx over 1 year ago | discuss
  12. OpenLLaMA 7B model trained on RedPajama dataset (twitter.com)
    4 points by yoquan over 1 year ago | discuss
  13. Lessons from fine-tuning RedPajama LLM on Slack data (www.union.ai)
    3 points by samhita-alla over 1 year ago | discuss
  14. What’s in the RedPajama-Data-1T LLM training set (simonwillison.net)
    3 points by notmysql_ over 1 year ago | discuss
  15. Fine-Tuning Insights: Lessons from Experimenting with RedPajama on Slack Data (www.union.ai)
    2 points by swiftlyTyped 9 months ago | discuss
  16. RedPajama training progress at 440B tokens (www.together.xyz)
    2 points by tim_sw over 1 year ago | discuss
  17. RedPajama-Data: Code for preparing large datasets (github.com)
    2 points by harrisonpowers over 1 year ago | discuss
  18. RedPajama-Data-v2: An open dataset with 30T tokens (2023) (www.together.ai)
    1 points by tosh 7 months ago | discuss
  19. RedPajama Data 1T (huggingface.co)
    1 points by tosh over 1 year ago | discuss
  20. Llama Llama RedPajama (openlibrary.org)
    1 points by nothrowaways over 1 year ago | discuss
  21. Show HN: finetune LLMs via the Finetuning Hub (github.com)
    80 points by rsaha7 about 1 year ago | 17 comments
  22. Show HN: I built an on-device LLM based chatbot for iPhones
    20 points by woadwarrior01 over 1 year ago | 6 comments
  23. Show HN: The fastest way to run Mixtral 8x7B on Apple Silicon Macs
    18 points by woadwarrior01 8 months ago | 22 comments
  24. Show HN: Finetuning LLMs: Open-source vs. Close-source
    2 points by rohit_saha about 1 year ago | 1 comments
  25. Llama 1.3B Trained on 200B Tokens for Commercial Use (huggingface.co)
    25 points by vsroy over 1 year ago | 7 comments
  26. Mosaic trained a 1B parameter model on 440 GPUs for 200B tokens (huggingface.co)
    2 points by ovaistariq over 1 year ago | discuss