Local AI with Docker's Testcontainers
โข
7
Joseph [open/acc] Pollack
Tonic
AI & ML interests
๐คMaking robots to help people learn things quicker ๐ฉ๐ปโ๐๐
Recent Activity
updated
a Space
about 19 hours ago
Tonic/Phi-4
updated
a collection
about 23 hours ago
cool models
liked
a dataset
about 23 hours ago
HumanLLMs/Human-Like-DPO-Dataset
Articles
Organizations
Tonic's activity
reacted to
hexgrad's
post with ๐
2 days ago
Post
5745
๐ฃ Looking for labeled, high-quality synthetic audio/TTS data ๐ฃ Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.
If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.
What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. โค๏ธ
More details at hexgrad/Kokoro-82M#21
If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.
What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. โค๏ธ
More details at hexgrad/Kokoro-82M#21
- 14 replies
reacted to
anakin87's
post with โค๏ธ
about 1 month ago
Post
1618
Tulu 3 SFT Mixture by AllenAI is a massive, good, multilingual dataset for fine-tuning Language Models.
Unfortunately, it was missing the "language" column.
I added it using the good old fastText.
Check out the dataset here ๐ anakin87/tulu-3-sft-mixture-with-language
Unfortunately, it was missing the "language" column.
I added it using the good old fastText.
Check out the dataset here ๐ anakin87/tulu-3-sft-mixture-with-language
- 1 reply
reacted to
merve's
post with ๐ง ๐โค๏ธ๐
about 2 months ago
Post
3157
your hugging face profile now has your recent activities ๐ค
posted
an
update
2 months ago
Post
3525
๐๐ปโโ๏ธhey there folks,
periodic reminder : if you are experiencing โ ๏ธ500 errors โ ๏ธ or โ ๏ธ abnormal
we have a thread ๐๐ป https://discord.com/channels/879548962464493619/1295847667515129877
if you can record the problem and share it there , or on the forums in your own post , please dont be shy because i'm not sure but i do think it helps ๐ค๐ค๐ค
periodic reminder : if you are experiencing โ ๏ธ500 errors โ ๏ธ or โ ๏ธ abnormal
spaces behavior on load or launch โ ๏ธwe have a thread ๐๐ป https://discord.com/channels/879548962464493619/1295847667515129877
if you can record the problem and share it there , or on the forums in your own post , please dont be shy because i'm not sure but i do think it helps ๐ค๐ค๐ค
- 2 replies
reacted to
davidberenstein1957's
post with ๐๐ค๐
2 months ago
Post
3094
Vector Search (most) datasets on the Hugging Face Hub ๐ฆ
Powered by: Polars, DuckDB, Gradio and model2vec (lightning-fast embeddings by Stรฉphan Tulkens).
Should work fast enough for datasets up to 100K.
davidberenstein1957/vectorsearch-hub-datasets
Powered by: Polars, DuckDB, Gradio and model2vec (lightning-fast embeddings by Stรฉphan Tulkens).
Should work fast enough for datasets up to 100K.
davidberenstein1957/vectorsearch-hub-datasets
reacted to
prithivMLmods's
post with ๐โค๏ธ
2 months ago
Post
5750
New Style, New Mix, New Drop ๐งค
๐งจFlux LoRA DLC: prithivMLmods/FLUX-LoRA-DLC
๐Glowing-Body: prithivMLmods/Glowing-Body-Flux-LoRA
๐Electric-Blue: prithivMLmods/Electric-Blue-Flux-LoRA
๐Intense-Red: prithivMLmods/Intense-Red-Flux-LoRA
๐Clouds-Illusion: prithivMLmods/Clouds-Illusion-Flux-LoRA
๐Digital-Yellow: prithivMLmods/Digital-Yellow-Flux-LoRA
๐งจFlux LoRA Collection: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
.
.
.
@prithivMLmods
๐งจFlux LoRA DLC: prithivMLmods/FLUX-LoRA-DLC
๐Glowing-Body: prithivMLmods/Glowing-Body-Flux-LoRA
๐Electric-Blue: prithivMLmods/Electric-Blue-Flux-LoRA
๐Intense-Red: prithivMLmods/Intense-Red-Flux-LoRA
๐Clouds-Illusion: prithivMLmods/Clouds-Illusion-Flux-LoRA
๐Digital-Yellow: prithivMLmods/Digital-Yellow-Flux-LoRA
๐งจFlux LoRA Collection: prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
.
.
.
@prithivMLmods
reacted to
m-ric's
post with ๐โค๏ธ๐๐ง
2 months ago
Post
2439
> Oasis: First Real-Time Video Game Without a Game Engine! ๐ฎ
DecartAI & Etched just released Oasis - a fully AI-generated video game running at 20 FPS (frames per second). The model takes keyboard inputs and generates everything - physics, rules, graphics - on the fly, without any game engine.
โก๏ธ What makes this special? Current text-to-video models (Mochi-1, Sora, Kling) generate about 1 frame every 10-20 seconds (that's the kind of device I had to play LoL back in the day, thus my low rankings). Oasis is 200 times faster, making it the first playable AI-generated game.
โ๏ธ Under the hood, it uses a vision transformer to encode space and a diffusion model to generate frames. The secret sauce is "dynamic noising" - a technique that keeps the video stable between frames.
Key insights:
โก๏ธ Generates 20 FPS, vs 0.2 FPS for other DIT-based video models
โฃ The specialized hardware Sohu developed by Etched allows to handle 10x more player than H100
๐ฎ Features real game mechanics
โฃ Movement, jumping, item management
โฃ Physics and lighting
โฃ Procedurally generated worlds
โ ๏ธ Current limitations
โฃ Blurry graphics at a distance
โฃ Objects sometimes change appearance
โฃ Memory issues in long sessions
Try it yourself, the playable demo is impressive! ๐ https://oasis.decart.ai/welcome
Code ๐ https://github.com/etched-ai/open-oasis
Read it in full ๐ https://oasis-model.github.io/
DecartAI & Etched just released Oasis - a fully AI-generated video game running at 20 FPS (frames per second). The model takes keyboard inputs and generates everything - physics, rules, graphics - on the fly, without any game engine.
โก๏ธ What makes this special? Current text-to-video models (Mochi-1, Sora, Kling) generate about 1 frame every 10-20 seconds (that's the kind of device I had to play LoL back in the day, thus my low rankings). Oasis is 200 times faster, making it the first playable AI-generated game.
โ๏ธ Under the hood, it uses a vision transformer to encode space and a diffusion model to generate frames. The secret sauce is "dynamic noising" - a technique that keeps the video stable between frames.
Key insights:
โก๏ธ Generates 20 FPS, vs 0.2 FPS for other DIT-based video models
โฃ The specialized hardware Sohu developed by Etched allows to handle 10x more player than H100
๐ฎ Features real game mechanics
โฃ Movement, jumping, item management
โฃ Physics and lighting
โฃ Procedurally generated worlds
โ ๏ธ Current limitations
โฃ Blurry graphics at a distance
โฃ Objects sometimes change appearance
โฃ Memory issues in long sessions
Try it yourself, the playable demo is impressive! ๐ https://oasis.decart.ai/welcome
Code ๐ https://github.com/etched-ai/open-oasis
Read it in full ๐ https://oasis-model.github.io/
reacted to
davanstrien's
post with ๐โค๏ธ
2 months ago
Post
2532
Excited to see my weird
davanstrien/ufo-ColPali dataset featured in a video by
@sabrinaesaquino
!
The video covers using ColPali with Binary Quantization in Qdant to accelerate retrieval. 2x speed up with no performance drop in results ๐ธ
Video: https://youtu.be/_A90A-grwIc?si=oB3JAhJG8VQUZGLz
Blog post: https://danielvanstrien.xyz/posts/post-with-code/colpali-qdrant/2024-10-02_using_colpali_with_qdrant.html
The video covers using ColPali with Binary Quantization in Qdant to accelerate retrieval. 2x speed up with no performance drop in results ๐ธ
Video: https://youtu.be/_A90A-grwIc?si=oB3JAhJG8VQUZGLz
Blog post: https://danielvanstrien.xyz/posts/post-with-code/colpali-qdrant/2024-10-02_using_colpali_with_qdrant.html
- 2 replies
