Yi-34B-200Khas enhanced the long text capability. In the Needle-in-a-Haystack test, the performance rises from 89.3% to 99.8%. @01AI_Yi continues to pretrain the model on 5B tokens long-context data mixture and demonstrates a near-all-green performance!
https://
github.com/01-ai/Yi?tab=r
eadme-ov-file#news
…
OPEN SOURCE
-
Yi-34B-200K Achieves 99.8% Performance in Long Context Test
By
–
-
Open source outlook: growth prospects and emerging challenges ahead
By
–
The outlook for open source? Growing, but there are challenges https://
computerweekly.com/news/366569553
/The-outlook-for-open-source-Growing-but-there-are-challenges?utm_source=dlvr.it&utm_medium=twitter
… #InternetOfThings #InternetTech #IoT -
New Script Competition Launched on HuggingFace Platform
By
–
A brand new script competition on HuggingFace: https://
huggingface.co/spaces/BVRA/Sn
akeCLEF2024
… -
Hugging Face Launches Open-Source Robotics Project with AI
By
–
Can't wait to empower everyone to build their own little robots thanks to open science and open-source AI. Welcome to the team @RemiCadene
! https://
venturebeat.com/ai/hugging-fac
e-is-launching-an-open-source-robotics-project-led-by-former-tesla-scientist/
… -
Celebrating Open-Source Robotics Growth and Community Development
By
–
Congrats! The world needs more open-source robotics!
-
MICS Launches CroissantLLM, Bilingual Open Source French-English Model
By
–
[#Article] Generative AI: MICS Launches CroissantLLM, a Bilingual Open Source French-English Model https://actuia.com/actualite/ia-generative-le-mics-lance-croissantllm-un-modele-open-source-bilingue-francais-anglais/
… #AI #ArtificialIntelligence #GenerativeAI -
Llama 7B Training on Single RTX 4090 GPU Memory Efficient
By
–
For the first time, we show that the Llama 7B LLM can be trained on a single consumer-grade GPU (RTX 4090) with only 24GB memory. This represents more than 82.5% reduction in memory for storing optimizer states during training. Training LLMs from scratch currently requires huge
-
MLX Axolotl Google Vertex AI frameworks comparison
By
–
MLX, Axolotl, Google vertex, depends on the cases
-
Silent Bugs in Fine-tuning: Attention to Detail Matters
By
–
Beautiful work / attention to detail trying to get Gemma to finetune correctly. There are so many foot guns here to be super careful with. All of these issues don't throw any errors, they silently make your network worse. A great example of what I wrote about in my "A Recipe for
-
LangChain Hiring for LLM Application Development Platform
By
–
We're hiring! We've built a great product on a small but mighty team, reaching 5M+ monthly downloads, 50K+ apps powered, and 2K+ contributors to our open source project. We've also recently GA launched LangSmith – our solution for LLM application development, monitoring, and