Hackernews posts about Code Llama

  1. Ask HN: How do you deploy Python-based LangChain or LlamaIndex code on prod?
    2 points by pinglin 18 days ago | 1 comments
  2. Show HN: Void - open source Cursor AI code editor (voideditor.com)
    13 points by andrewpareles 8 days ago | 8 comments
  3. Deploy a custom Llama 3 API in 15 lines of code (lightning.ai)
    1 points by wfalcon 27 days ago | discuss
  4. Show HN: Sourcetable – AI Spreadsheet and Data Platform
    130 points by mceoin 1 day ago | 62 comments
  5. Show HN: Wat Dat – A Firefox Extension for Instant Text Explanations (addons.mozilla.org)
    32 points by bsgada 16 days ago | 18 comments
  6. Show HN: KTransformers–236B Model and 1M Context LLM Inference on Local Machines (github.com)
    20 points by sssummer 22 days ago | 3 comments
  7. Show HN: Automatic chaptering – From raw transcripts to structured documents (huggingface.co)
    5 points by Yannael 11 days ago | discuss
  8. Discuss HN: Will 100M token LLMs replace most programmers?
    3 points by Mariciano 20 days ago | 6 comments
  9. Show HN: Build event-driven workflows with Python async functions (github.com)
    3 points by gusye 3 days ago | discuss
  10. Show HN: An optimizing model router with easy BYOK and serverless inference (keytrustee.org)
    1 points by CuriouslyC 12 days ago | discuss
  11. Ask HN: Linux-Compat Hardware for Self-Hosted AI Models & gen advice
    1 points by eth0up 28 days ago | discuss
  12. Build a quick Local code intelligence using Ollama with Rust (bosun.ai)
    17 points by tinco 14 days ago | 1 comments
  13. An open-source AI code assistant inside your editor (ollama.com)
    3 points by crbelaus 20 days ago | discuss
  14. OpenAI is good at unminifying code (glama.ai)
    931 points by punkpeye 22 days ago | 304 comments
  15. Code Llama, a state-of-the-art large language model for coding (ai.meta.com)
    970 points by marcopicentini about 1 year ago | 501 comments
  16. Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B (www.phind.com)
    813 points by rushingcreek about 1 year ago | 285 comments
  17. Code Llama, a state-of-the-art large language model for coding (ai.meta.com)
    673 points by nickthegreek about 1 year ago | 2 comments
  18. Meta AI releases Code Llama 70B (twitter.com)
    598 points by albert_e 8 months ago | 294 comments
  19. Show HN: Use Code Llama as Drop-In Replacement for Copilot Chat (continue.dev)
    187 points by sestinj about 1 year ago | 52 comments
  20. Understanding Llama 2 and the New Code Llama LLMs (magazine.sebastianraschka.com)
    170 points by rasbt about 1 year ago | 34 comments
  21. SlowLlama: Finetune llama2-70B and codellama on MacBook Air without quantization (github.com)
    156 points by behnamoh 12 months ago | 54 comments
  22. Show HN: Open Interpreter – CodeLlama in your terminal, executing code (openinterpreter.com)
    82 points by killianlucas about 1 year ago | 21 comments
  23. Workers AI Update: Stable Diffusion, Code Llama and Workers AI in 100 Cities (blog.cloudflare.com)
    77 points by todsacerdoti 10 months ago | 32 comments
  24. Ask HN: Code Llama 70B on a dedicated server
    67 points by lavren1974 7 months ago | 42 comments
  25. Show HN: I built local copilot alternative using Codellama (marketplace.visualstudio.com)
    38 points by ex3ndr 10 months ago | 6 comments
  26. A complete guide to fine-tuning Code Llama (ragntune.com)
    32 points by slhui about 1 year ago | 1 comments
  27. Full F16 precision 34B Code Llama at >20T/s on M2 Ultra (twitter.com)
    17 points by Jimmc414 about 1 year ago | 2 comments
  28. Meta launches own AI code-writing tool: Code Llama (www.theverge.com)
    15 points by jamesponddotco about 1 year ago | 1 comments
  29. Run Code Llama Locally (ollama.ai)
    12 points by jmorgan about 1 year ago | 4 comments
  30. Code Llama (ai.meta.com)
    12 points by jkw about 1 year ago | 3 comments
  31. Prompting Code Llama (ollama.ai)
    10 points by jmorgan about 1 year ago | discuss
  32. Meta is releasing a new CodeLlama (www.facebook.com)
    8 points by senthilnayagam 8 months ago | 2 comments
  33. OpenAI Lifeboat – Proxy OpenAI Code to Llama 70B on Replicate (lifeboat.replicate.dev)
    6 points by Charlieholtz 10 months ago | 3 comments
  34. Comparing Code Llama Models Locally (about.xethub.com)
    5 points by skadamat about 1 year ago | discuss
  35. Code Llama for VS Code (github.com)
    4 points by hcrisp about 1 year ago | discuss
  36. Meta releases Code Llama, a code-generating AI model (techcrunch.com)
    4 points by CharlesW about 1 year ago | discuss
  37. M2 Ultra runs codellama 34B F16 at 150 token per second (twitter.com)
    3 points by behnamoh 11 months ago | 3 comments
  38. Ask HN: Why the LLaMA code base is so short
    3 points by kureikain 10 months ago | 2 comments
  39. CodeCapybara: Code Writing LLaMa Finetuned on Deepmind Dataset (github.com)
    3 points by brucethemoose2 over 1 year ago | 1 comments
  40. Run CodeLlama on a Serverless GPU (github.com)
    3 points by Mernit about 1 year ago | discuss
  41. Fine-tuned CodeLlama beats GPT-4 on HumanEval (huggingface.co)
    3 points by jumploops about 1 year ago | discuss
  42. Show HN: I reproduced Code Llama fill-in-the-middle code completion training (github.com)
    2 points by BohdanPetryshyn 3 months ago | discuss
  43. CodeGemma vs. CodeLlama (msty.app)
    2 points by chown 5 months ago | discuss
  44. Local terminal companion, powered by CodeLLaMa (github.com)
    2 points by johanneswu 7 months ago | discuss