Why PyThagorean? ๐
โข
7
Prithiv Sakthi PRO
prithivMLmods
AI & ML interests
computer vision, multimodality, realism engine adapters @starngerzonehf
Recent Activity
new activity
21 minutes ago
onnx-community/convert-to-onnx:Upload ONNX to Your Current Model Repo ๐
updated
a model
41 minutes ago
prithivMLmods/FastThink-0.5B-Tiny
liked
a model
about 1 hour ago
prithivMLmods/Deep-Fake-Detector-Model-ONNX
Articles
Organizations
prithivMLmods's activity
reacted to
not-lain's
post with ๐ค
about 17 hours ago
Post
1263
I have just released a new blogpost about kv caching and its role in inference speedup ๐
๐ https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :
๐ https://huggingface.co/blog/not-lain/kv-caching/
some takeaways :
- 4 replies
reacted to
hexgrad's
post with ๐๐๐๐
1 day ago
Post
3432
hexgrad/Kokoro-82M got an upgrade! โฌ๏ธ More voices, more languages,
GitHub: https://github.com/hexgrad/kokoro
PyPI: https://pypi.org/project/kokoro/
Space: hexgrad/Kokoro-TTS
pip install kokoro, and still 82M parameters.GitHub: https://github.com/hexgrad/kokoro
PyPI: https://pypi.org/project/kokoro/
Space: hexgrad/Kokoro-TTS
- 6 replies
replied to
their
post
1 day ago
Iโm not sure, but if context continues to evolve in the future, the real OpenAI will improve more and more compared to paid AI providers. People will increasingly use open-source models for their domain-specific tasks.
posted
an
update
1 day ago
Post
3014
Deepswipe by
.
.
.
. Deepseek๐ฌ๐ฟ
Everything is now in recovery. ๐๐
.
.
.
. Deepseek๐ฌ๐ฟ
Everything is now in recovery. ๐๐
-
- 3 replies
reacted to
AdinaY's
post with ๐ฅ
2 days ago
Post
2522
Itโs not just a flood of model releases, papers are dropping just as fast ๐
Here are the 10 most upvoted papers from the Chinese community:
๐ zh-ai-community/2025-january-papers-679933cbf0f3ced11f5a168a
Here are the 10 most upvoted papers from the Chinese community:
๐ zh-ai-community/2025-january-papers-679933cbf0f3ced11f5a168a
reacted to
m-ric's
post with ๐ฅ
2 days ago
Post
2807
๐ง๐ต๐ฒ ๐๐๐ฏ ๐๐ฒ๐น๐ฐ๐ผ๐บ๐ฒ๐ ๐ฒ๐
๐๐ฒ๐ฟ๐ป๐ฎ๐น ๐ถ๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ ๐ฝ๐ฟ๐ผ๐๐ถ๐ฑ๐ฒ๐ฟ๐!
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Read more in the announcement ๐ https://huggingface.co/blog/inference-providers
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Read more in the announcement ๐ https://huggingface.co/blog/inference-providers
- 1 reply
Incredible stat ๐
reacted to
victor's
post with ๐
2 days ago
Post
2745
Finally, an open-source AI that turns your lyrics into full songs is hereโmeet YuE! Unlike other tools that only create short clips, YuE can make entire songs (up to 5 minutes) with vocals, melody, and instruments all working together. Letsss go!
m-a-p/YuE-s1-7B-anneal-en-cot
m-a-p/YuE-s1-7B-anneal-en-cot
- 1 reply
reacted to
clem's
post with โค๏ธ
3 days ago
Post
6654
AI is not a zero-sum game. Open-source AI is the tide that lifts all boats!
reacted to
fdaudens's
post with โค๏ธ
3 days ago
Post
7543
Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5Mโnearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. ๐
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version โ 1M downloads alone.
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5Mโnearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. ๐
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version โ 1M downloads alone.
-
- 4 replies
reacted to
nicolay-r's
post with ๐ฅ
4 days ago
Post
1734
๐ข For those who wish to apply DeepSeek-R1 for handling tabular / streaming data using schema of prompts (CoT), the OpenRouter AI hosts API for accessing:
https://openrouter.ai/deepseek/deepseek-r1
The no-string option to quick start with using DeepSeek-R1 includes three steps:
โ OpenRouter provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/open_router.py
โ Bulk-chain for infering data: https://github.com/nicolay-r/bulk-chain
โ Json Schema for Chain-of-Though reasoning (see screenshot ๐ท below)
๐บ below is a screenshot of how to quick start the demo, in which you can test your schema for LLM responses. It would ask to type all the parameters first for completing the requests (which is
๐ To apply it for JSONL/CSV data, you can use
โณ As for time, OpenRouter finds me relatively slow with 30~40 seconds per request
Models:
deepseek-ai/DeepSeek-R1
https://openrouter.ai/deepseek/deepseek-r1
The no-string option to quick start with using DeepSeek-R1 includes three steps:
โ OpenRouter provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/open_router.py
โ Bulk-chain for infering data: https://github.com/nicolay-r/bulk-chain
โ Json Schema for Chain-of-Though reasoning (see screenshot ๐ท below)
๐บ below is a screenshot of how to quick start the demo, in which you can test your schema for LLM responses. It would ask to type all the parameters first for completing the requests (which is
text within this example).๐ To apply it for JSONL/CSV data, you can use
--src shell parameter for passing the related fileโณ As for time, OpenRouter finds me relatively slow with 30~40 seconds per request
Models:
deepseek-ai/DeepSeek-R1
-
- 1 reply
reacted to
AdinaY's
post with ๐ฅ
6 days ago
Post
1322
Baichuan is making big moves today ๐ฅ
โจ Launched All-Scenario Reasoning Model (language, visual, and search reasoning capabilities) , with medical expertise as one of its key highlights.
https://ying.baichuan-ai.com/chat
โจ Released Baichuan-M1-14B Medical LLM on the hub
Available in both Base and Instruct versions, support English & Chinese.
Model:
baichuan-inc/Baichuan-M1-14B-Base
baichuan-inc/Baichuan-M1-14B-Instruct
โจ Launched All-Scenario Reasoning Model (language, visual, and search reasoning capabilities) , with medical expertise as one of its key highlights.
https://ying.baichuan-ai.com/chat
โจ Released Baichuan-M1-14B Medical LLM on the hub
Available in both Base and Instruct versions, support English & Chinese.
Model:
baichuan-inc/Baichuan-M1-14B-Base
baichuan-inc/Baichuan-M1-14B-Instruct
reacted to
burtenshaw's
post with ๐คฏ
7 days ago
Post
2082
AI was built on side projects!
reacted to
AdinaY's
post with ๐ฅ
7 days ago
Post
1389
VideoLLaMA 3๐ฅmultimodal foundation models for Image and Video Understanding by DAMO Alibaba
Model: DAMO-NLP-SG/videollama3-678cdda9281a0e32fe79af15
Paper: VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (2501.13106)
โจ 2B/7B
โจ Apache2.0
Model: DAMO-NLP-SG/videollama3-678cdda9281a0e32fe79af15
Paper: VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (2501.13106)
โจ 2B/7B
โจ Apache2.0
- 1 reply
reacted to
AdinaY's
post with ๐ง
8 days ago
Post
2531
UI-TARS ๐ฅ series of native GUI agent models (2B/7B/72B) released by ByteDance, combining perception, reasoning, grounding, and memory into one system.
Model: https://huggingface.co/bytedance-research
Paper: UI-TARS: Pioneering Automated GUI Interaction with Native Agents (2501.12326)
Model: https://huggingface.co/bytedance-research
Paper: UI-TARS: Pioneering Automated GUI Interaction with Native Agents (2501.12326)
reacted to
sharpenb's
post with ๐
8 days ago
Post
1843
We compressed SmolLMs to make 135 variations of them (see https://huggingface.co/PrunaAI?search_models=smolLM) with different quantization configurations with
We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
pruna (https://docs.pruna.ai/en/latest/). We made a blog to summarize our findings (see https://www.pruna.ai/blog/smollm2-smaller-faster) and small LM can be made smaller! :)
- 3 replies
reacted to
JingzeShi's
post with ๐ฅ
9 days ago
Post
1593
๐คฉwarmup -> stable -> decay leanring rate scheduler:
๐use the Stable Phase CheckPoints to Continue Training the model on Any New Dataset without spikes of the training!!!
JingzeShi/Doge-20M-checkpoint
JingzeShi/Doge-60M-checkpoint
๐use the Stable Phase CheckPoints to Continue Training the model on Any New Dataset without spikes of the training!!!
JingzeShi/Doge-20M-checkpoint
JingzeShi/Doge-60M-checkpoint
-
- 4 replies