Hackernews posts about Mistral 7B

Mistral 7B is an artificial intelligence model used for generating intermediate output in Magic: The Gathering draft simulations.

1. Show HN: 1k desktop beats vendor sparse library 474× on Mistral-7B (rolv.ai)
   1 points by heggenhougen 23 days ago | 1 comments
2. Tq-KV – Rust implementation of TurboQuant that works on GGUF models
   3 points by onurgokyildiz 8 days ago | discuss
3. Run Mistral 7B model using less than 4GB of memory on your Mac with CoreML (huggingface.co)
   14 points by mnoorfawi over 1 year ago | discuss
4. Mistral-7B-v0.3 released on HuggingFace (huggingface.co)
   9 points by cuuupid almost 2 years ago | discuss
5. Meltemi-7B: A Large Language Model for Greek Built on Top of Mistral-7B (medium.com)
   4 points by NKosmatos almost 2 years ago | discuss
6. Show HN: Mistral-7B training using pyspark,DeepSpeed (github.com)
   2 points by gituser123 8 months ago | discuss
7. Fine-tune large models like Mistral-7B, Llama-2-13B, Phi-2, or Qwen-14B for free (github.com)
   2 points by lawrenceyan over 1 year ago | discuss
8. Representation Engineering Mistral-7B an Acid Trip (vgel.me)
   2 points by freeqaz over 1 year ago | discuss
9. LLaMa 3 vs. Mistral 7B: A Head-to-Head AI Showdown (medium.com)
   2 points by lijunhao almost 2 years ago | discuss
10. Fine-Tuning Mistral-7B on Apple Silicon: A Mac User's Journey with Axolotl LoRA (medium.com)
    1 points by jgtor 9 months ago | discuss
11. Show HN: I built a free in-browser Llama 3 chatbot powered by WebGPU (github.com)
    547 points by abi almost 2 years ago | 139 comments
12. Show HN: Knowledge graph of restaurants and chefs, built using LLMs (theophilecantelob.re)
    201 points by theophilec about 1 year ago | 39 comments
13. Ask HN: What do you do with Local LLMs?
    17 points by rkwz almost 2 years ago | 19 comments
14. Show HN: Building a Real-Time AI Avatar for Coaching and Training Simulations (coaching.cerebrium.ai)
    6 points by cartesia over 1 year ago | 1 comments
15. Show HN: Use local LLMs to organize your files (github.com)
    6 points by hyperfield 9 months ago | discuss
16. Show HN: AI Runner – my personal opensource, local, multi-modal, AI assistant (twitter.com)
    4 points by _7eg9 almost 2 years ago | 2 comments
17. Show HN: We open sourced Verbis, a local AI assistant with SaaS connectors (github.com)
    4 points by alexmavr over 1 year ago | discuss
18. Show HN: Local AI document intelligence – no cloud, runs on your machine (unidocverse.com)
    3 points by bommavj about 2 months ago | discuss
19. Show HN: WebPizza – AI/RAG pipeline running in the browser with WebGPU (github.com)
    3 points by stramanu 5 months ago | discuss
20. Tell HN: We've come a long way since GPT-3 days
    3 points by behnamoh 11 months ago | discuss
21. Show HN: 100% LLM accuracy–no fine-tuning, JSON only (github.com)
    2 points by MysticBirdie about 1 month ago | 2 comments
22. Show HN: HuggingFaceModelDownloader v2.0–resumable, filterable HF Downloads (github.com)
    1 points by bodaay 7 months ago | discuss
23. Show HN: Podyssey, a smart search engine for podcasts (www.podyssey.com)
    1 points by 2403tales over 1 year ago | discuss
24. Show HN: LLM Fine-tuning platform with integrated data labeling (ubiai.tools)
    1 points by Mesterniz over 1 year ago | discuss
25. Show HN: AiDAPal – An IDA Pro plugin and fine-tuned LLM for reverse engineering (github.com)
    1 points by avgbusinessuser almost 2 years ago | discuss
26. Mistral releases the v0.3 of its 7B LLM (huggingface.co)
    6 points by fgfm almost 2 years ago | discuss
27. Constant 14ms attention: 512→524K tokens (24.5x faster than FlashAttention) (github.com)
    1 points by luxiedge 2 months ago | 1 comments
28. Mistral raises 1.7B€, partners with ASML (mistral.ai)
    802 points by TechTechTech 7 months ago | 424 comments
29. Mistral AI raises 1.7B€ (mistral.ai)
    132 points by kgwgk 7 months ago | 3 comments
30. Show HN: Beating SOTA embeddings on DeepMind's LIMIT benchmark (94% vs. 18%) (github.com)
    1 points by sangeet01 4 months ago | discuss
31. Mathstral: 7B LLM designed for math reasoning and scientific discovery (mistral.ai)
    33 points by mnoorfawi over 1 year ago | discuss
32. Ask HN: Best foundation model for CLM fine-tuning?
    28 points by philomath868 7 months ago | 19 comments