Hackernews posts about LLaMA 7B

1. Show HN: Knowledge graph of restaurants and chefs, built using LLMs (theophilecantelob.re)
   201 points by theophilec 27 days ago | 39 comments
2. Show HN: Tool to automatically write Git commit messages locally using LLMs (ollama.com)
   2 points by vituu 25 days ago | discuss
3. M2 Ultra can run 128 streams of Llama 2 7B in parallel (github.com)
   268 points by behnamoh over 1 year ago | 173 comments
4. The tide is shifting: 1.3B outperforms 7B Llama 2 (arxiv.org)
   63 points by __vec__ over 1 year ago | 15 comments
5. EagleX 1.7T: Soaring past LLaMA 7B 2T in both English and Multi-lang evals (substack.recursal.ai)
   36 points by lhofer about 1 year ago | 9 comments
6. Jlama (Java) outperforms llama.cpp in F32 Llama 7B Model (twitter.com)
   7 points by tjake over 1 year ago | 9 comments
7. Falcon 40B/7B Outperforms LLaMA 65B/7B, but with restrictions on commercial use (huggingface.co)
   4 points by brucethemoose2 almost 2 years ago | 3 comments
8. Puma: Secure Inference of LLaMA-7B in Five Minutes (huggingface.co)
   4 points by tosh over 1 year ago | 1 comments
9. We Fine-Tuned a LlaMA 7B Language Model to Use GraphQL APIs (weaviate.io)
   4 points by edichief over 1 year ago | discuss
10. What’s the difference between Llama 2 7B, 13B, and 70B? (replicate.com)
    4 points by Charlieholtz over 1 year ago | discuss
11. I Conducted Experiments with the Alpaca/LLaMA 7B Language Model (hackernoon.com)
    4 points by TakakiTohno almost 2 years ago | discuss
12. Mistral AI 7B – beats Llama 2 7B and 13B (www.mystic.ai)
    3 points by paulcjh over 1 year ago | 3 comments
13. Phi-1.5 (1.3B Outperforms Llama 2 7B) (huggingface.co)
    3 points by jcuenod over 1 year ago | 3 comments
14. MLX: Fine-tune Llama 7B or Mistral 7B with 32GB (github.com)
    3 points by tosh over 1 year ago | discuss
15. Llama-2-7B-chat-mlx for Apple’s new MLX framework (huggingface.co)
    3 points by CodeCat over 1 year ago | discuss
16. Fine-tune large models like Mistral-7B, Llama-2-13B, Phi-2, or Qwen-14B for free (github.com)
    2 points by lawrenceyan 7 months ago | discuss
17. Ask HN: Llama-2-7B adapter merged with llama-2-7B-chat model?
    2 points by dynamo_ 11 months ago | discuss
18. Devin fine tuning a 7B llama model (twitter.com)
    2 points by quick_brown_fox about 1 year ago | discuss
19. Fine-tuned Llama 2 7B to analyze 10-K financial reports and write funny tweets (gist.github.com)
    2 points by smiagkyi over 1 year ago | discuss
20. Llama-2-7B-32K-Instruct – and fine-tuning for Llama-2 models with Together API (together.ai)
    2 points by gfortaine over 1 year ago | discuss
21. Sleeper agent: a proof-of-concept llama 7B finetune with a codephrase backdoor (twitter.com)
    2 points by spr-alex almost 2 years ago | discuss
22. Show HN: A script to deploy Llama7B on A10 Batch size 1 100 Token per sec (github.com)
    1 points by mattick27 over 1 year ago | discuss
23. Fine tune Llama 2 (7B) with an API (replicate.com)
    1 points by Charlieholtz over 1 year ago | discuss
24. Fine-tune your own Llama 2 to replace GPT-3.5/4
    955 points by kcorbitt over 1 year ago | 181 comments
25. Ask HN: Who is using small OS LLMs in production?
    50 points by alaeddine-13 over 1 year ago | 55 comments
26. Tell HN: Llama 33B is the Tower of Babel. It's time to celebrate
    16 points by rasengan almost 2 years ago | 4 comments
27. Gorilla: LLMs Connected to APIs Explained
    9 points by CShorten over 1 year ago | 2 comments
28. Number of Token per Second Calculations
    6 points by mersawi over 1 year ago | 3 comments
29. Ask HN: Best local LLM to summarize web pages?
    6 points by smusamashah 12 months ago | 1 comments
30. Show HN: Memora – A Vector DB with Multistage Reranking (www.usememora.app)
    5 points by matusa over 1 year ago | 3 comments
31. Tell HN: We take LLMs and Diffusion models for granted
    5 points by behnamoh over 1 year ago | 2 comments
32. Show HN: Use Purple LLaMA to test ChatGPT safeguards
    4 points by saqadri over 1 year ago | 1 comments