Joined October 2022
- Tweets 171
- Following 6
- Followers 9,100
- Likes 14
51 Photos and videos
8 Dec 2023
mixtral-8x7b-32kseqlen from @MistralAI. Mixture of Experts? 🤔
x.com/MistralAI/status/17331…
8 Dec 2023
magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp:/%2Fopentracker.i2p.rocks:6969/announce&tr=http:/%https://t.co/g0m9cEUz0T:80/announce
RELEASE a6bbd9affe0c2725c1b7410d66833e24
1
2
7
14,680
8 Dec 2023
8 Dec 2023
New open weights LLM from @MistralAI
params.json:
- hidden_dim / dim = 14336/4096 => 3.5X MLP expand
- n_heads / n_kv_heads = 32/8 => 4X multiquery
- "moe" => mixture of experts 8X top 2 👀
Likely related code:
github.com/mistralai/megablo…
Oddly absent: an over-rehearsed professional release video talking about a revolution in AI.
If people are wondering why there is so much AI activity right around now, it's because the biggest deep learning conference (NeurIPS) is next week.
10
1,937
19 Apr 2023
NVIDIA announces model for high-resolution text to video generation. It can generate videos with resolution up to 1280 x 2048.
4
6
35
5,843
19 Apr 2023
Source: research.nvidia.com/labs/tor…
Samples: research.nvidia.com/labs/tor…
2
2,604
19 Apr 2023
StabilityAI released StableLM: an open source LLM with 3b and 7b parameters. RLHF and larger models coming soon.
1
15
2,395
18 Apr 2023
Meta releases DINOv2 the first method for training computer vision models that uses self-supervised learning (no labeling needed) to achieve industry standard results.
1
11
2,136
12 Apr 2023
OpenAI released Consistency Models: a new family of generative models that support fast one-step generation of images.
1
1
19
3,188
5 Apr 2023
Meta releases the Segment Anything Project:
- SA-1B dataset containing 1-Billion segmentation masks
- Segment Anything Model (SAM) for general image and video segmentation
1
18
2,366
5 Apr 2023
Announcement: ai.facebook.com/blog/segment…
Code: github.com/facebookresearch/…
Demo: segment-anything.com/
1
1,226
24 Mar 2023
Databricks open-sources Dolly: a 6b instruction-tuned LLM similar to ChatGPT. It's built off of EleutherAI's GPT-J-6B.
2
4
51
4,567
20 Mar 2023
Damo releases an open-source text to video model with 1.7B parameters. The demo only requires 16GB CPU RAM and 16GB GPU RAM to run. Try it out on Hugging Face below:
2
3
19
2,584
20 Mar 2023
Researchers introduce Video-P2P: Video Editing with
Cross-attention Control.
1
2
15
2,687
16 Mar 2023
Microsoft introduces 365 Copilot - bringing AI assistance into Word, PowerPoint, Excel, Outlook, Teams, Viva, and Power Platform.
2
1
27
3,761