Skip to content

AI Dynamics

Global AI News Aggregator

Rechercher

OPEN SOURCE

Yi-Coder Open-Sourced: Compact LLM for Coding Performance

By

@01ai_yi

–

05 September 2024 5h14

🚀 Yi-Coder is open-sourced!

The 'Small but Mighty' LLM offers SOTA coding performance under 10B parameters. Excel in code editing, completion, debugging, and math reasoning.

✅ 2 sizes: 9B & 1.5B (Chat & Base)
✅ 128K context length
✅ Support 52 programming languages

Explore… pic.twitter.com/QVscshn6PE
— Yi-01.AI (@01AI_Yi) 5 septembre 2024

🚀 Yi-Coder is open-sourced! The 'Small but Mighty' LLM offers SOTA coding performance under 10B parameters. Excel in code editing, completion, debugging, and math reasoning. ✅ 2 sizes: 9B & 1.5B (Chat & Base) ✅ 128K context length ✅ Support 52 programming languages Explore it now👇 huggingface.co/collections/0… #YiCoder #01AI #LLMs #OpenSource

→ View original post on X — @01ai_yi, 2024-09-05 03:14 UTC

5 September 2024
Unsloth and Axolotl: Best Fine-Tuning Options Comparison

By

@maximelabonne

–

05 September 2024 0h57

Then Unsloth and Axolotl are your best options imo. There's no difference in terms of PEFT/FFT. I think Spectrum is only supported by Axolotl at the moment if you're interested.

→ View original post on X — @maximelabonne

5 September 2024
Unsloth vs Axolotl: Choosing the Right Fine-Tuning Framework

By

@maximelabonne

–

04 September 2024 23h36

In general, I'd recommend Unsloth for single-GPU settings and Axolotl for multi-GPU settings. For research, you might want to have more fine-grained control though. TRL works there, but reimplementing it in PyTorch is also a good option for full control.

→ View original post on X — @maximelabonne

4 September 2024
CEO shares Llama 405B record performance at Global AI Summit

By

@sambanovaai

–

04 September 2024 22h30

Our team will be at @globalaisummit 2024 next week where our CEO & Co-Founder, @RodrigoLiang
, will share more about our world record performance on the best open source model, Llama 405B. See you at #GAIN2024! Learn more https://
globalaisummit.org/en/default.aspx #AI #LLM

→ View original post on X — @sambanovaai

4 September 2024
Top 10 Hugging Face Creator Celebrates Milestone with Community

By

@maximelabonne

–

04 September 2024 19h16

I almost missed it but I broke into the top 10 most followed accounts on @huggingface It's been a wild journey and I'm really happy where I am right now 🙂 Thanks everyone, you made it possible! And no worries: more articles, models, and datasets to come.

→ View original post on X — @maximelabonne

4 September 2024
PaliGemma Vision Language Model Implementation for Android

By

@_akhaliq

–

04 September 2024 17h24

PaliGemma Android HF github: https://
github.com/NSTiwari/PaliG
emma-Android-HF
… This repository is an implementation of inferring the PaliGemma Vision Language Model on Android using Hugging Face-Gradio Client API for tasks such as zero-shot object detection, image captioning and visual

→ View original post on X — @_akhaliq

4 September 2024
MarioVGG: Text-to-Video Diffusion Model for Super Mario Generation

By

@_akhaliq

–

04 September 2024 17h16

MarioVGG

Video Game Generation: A Practical Study using Mario

model: https://t.co/rEBEwTpkEr

present MarioVGG, a text-to-video diffusion model for controllable video generation on the Super Mario Bros game. MarioVGG demonstrates the ability to continuously generate consistent… pic.twitter.com/LKjTgZIX8d
— AK (@_akhaliq) 4 septembre 2024

MarioVGG Game Generation: A Practical Study using Mario model: https://
huggingface.co/virtuals-proto
col/mario-videogamegen
… present MarioVGG, a text-to-video diffusion model for controllable video generation on the Super Mario Bros game. MarioVGG demonstrates the ability to continuously generate consistent

→ View original post on X — @_akhaliq

4 September 2024
Nvidia LlamaIndex Developer Contest RAG Applications Opportunity

By

@krishnaik06

–

04 September 2024 13h48

Check out this amazing opportunity to participate in the Nvidia and LlamaIndex Developer Contest where they encourage you to build retrieval-augmented generation (RAG), agentic, or beyond-agentic RAG applications in any domain.
Regissterlation link: https://
developer.nvidia.com/llamaindex-dev
eloper-contest?ncid=ref-inor-494422
…

→ View original post on X — @krishnaik06

4 September 2024
Redbrick Secures U.S. Patent for Open Metaverse Creation System

By

@pandeyajay7

–

04 September 2024 2h25

Redbrick Secures U.S. Patent for "Open #Metaverse Creation System" https://
prn.to/3Xte0WV

→ View original post on X — @pandeyajay7

4 September 2024
FastHTML Documentation Standards for LLM Integration

By

@jeremyphoward

–

03 September 2024 23h57

The FastHTML project follows these two proposals for its documentation. For instance, here is the FastHTML docs llms.txt: https://
docs.fastht.ml/llms.txt
And an LLM-ready context file: https://
docs.fastht.ml/llms-ctx.txt
All nbdev projects now create .md versions of all pages by default.

→ View original post on X — @jeremyphoward

3 September 2024

←Previous Page

1 … 696 697 698 699 700 … 1,291

INNOVATION GENERATIVE AI RESEARCH LLMS TOOLS MACHINE LEARNING CODE MARKET TRENDS TECHNOLOGY BUSINESS BIG TECH ETHICS ENTERPRISE AI SOFTWARE AGENTS AUTOMATION APPS COMPUTING DATA POLICY OPEN SOURCE MULTIMODAL AI REGULATION CULTURE CREATIVE AI PROMPT ENGINEERING SOCIETY ECONOMY SAFETY EDUCATION INVESTMENT AI HARDWARE AGI HARDWARE JOBS STARTUPS INDUSTRY ROBOTICS WORKFORCE SECURITY CYBERSECURITY HEALTHCARE AI SYSTEMS SUSTAINABILITY WEB3 DECENTRALIZED AI

AI Dynamics

Global AI News Aggregator

About
Archives
Contact

Rechercher