Why PyThagorean? π
β’
7
Prithiv Sakthi PRO
prithivMLmods
AI & ML interests
computer vision, multimodality, realism engine adapters @starngerzonehf
Recent Activity
new activity
42 minutes ago
prithivMLmods/Taurus-Opus-7B:Adding Evaluation Results
updated
a model
42 minutes ago
prithivMLmods/Taurus-Opus-7B
updated
a dataset
about 1 hour ago
prithivMLmods/Deepthink-Reasoning
Articles
Organizations
prithivMLmods's activity
reacted to
clem's
post with β€οΈ
about 3 hours ago
Post
504
AI is not a zero-sum game. Open-source AI is the tide that lifts all boats!
reacted to
fdaudens's
post with β€οΈ
about 3 hours ago
Post
417
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? 2.5Mβnearly 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. π
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version β 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? 2.5Mβnearly 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. π
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version β 1M downloads alone.
reacted to
nicolay-r's
post with π₯
about 11 hours ago
Post
860
π’ 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:
β OpenRouter provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/open_router.py
β Bulk-chain for infering data: https://github.com/nicolay-r/bulk-chain
β Json Schema for Chain-of-Though reasoning (see screenshot π· below)
πΊ 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
π To apply it for JSONL/CSV data, you can use
β³ 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:
β OpenRouter provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/open_router.py
β Bulk-chain for infering data: https://github.com/nicolay-r/bulk-chain
β Json Schema for Chain-of-Though reasoning (see screenshot π· below)
πΊ 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).π To apply it for JSONL/CSV data, you can use
--src shell parameter for passing the related fileβ³ As for time, OpenRouter finds me relatively slow with 30~40 seconds per request
Models:
deepseek-ai/DeepSeek-R1
reacted to
AdinaY's
post with π₯
3 days ago
Post
1242
Baichuan is making big moves today π₯
β¨ 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
β¨ 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
β¨ 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
β¨ 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 π€―
4 days ago
Post
1959
AI was built on side projects!
reacted to
AdinaY's
post with π₯
4 days ago
Post
1328
VideoLLaMA 3π₯multimodal 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)
β¨ 2B/7B
β¨ Apache2.0
Model: DAMO-NLP-SG/videollama3-678cdda9281a0e32fe79af15
Paper: VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (2501.13106)
β¨ 2B/7B
β¨ Apache2.0
- 1 reply
reacted to
AdinaY's
post with π§
4 days ago
Post
2489
UI-TARS π₯ 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 π
5 days ago
Post
1831
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 π₯
6 days ago
Post
1553
π€©warmup -> stable -> decay leanring rate scheduler:
πuse 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
πuse 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
reacted to
davidberenstein1957's
post with π₯
6 days ago
Post
1830
The RAG's in the bag!
You can now use the Synthetic Data Generator with your own domain-specific seed data to generate a dataset for fine-tuning retrieval or reranking models.
GitHub: https://buff.ly/49IDSmd
Spaces: https://buff.ly/3Y1S99z
Blog: https://huggingface.co./blog/sdiazlor/fine-tune-modernbert-for-rag-with-synthetic-data
You can now use the Synthetic Data Generator with your own domain-specific seed data to generate a dataset for fine-tuning retrieval or reranking models.
GitHub: https://buff.ly/49IDSmd
Spaces: https://buff.ly/3Y1S99z
Blog: https://huggingface.co./blog/sdiazlor/fine-tune-modernbert-for-rag-with-synthetic-data
- 1 reply
posted
an
update
7 days ago
Post
3056
Q'n' Sketches β€οΈβπ₯
πΌοΈ Adapters:
- Qs : strangerzonehf/Qs-Sketch
- Qd : strangerzonehf/Qd-Sketch
- Qx : strangerzonehf/Qx-Art
- Qc : strangerzonehf/Qc-Sketch
- Bb : strangerzonehf/Bg-Bag
π Collection : strangerzonehf/q-series-sketch-678e3503bf3a661758429717
πPage : https://huggingface.co./strangerzonehf
.
.
.
@prithivMLmods π€
πΌοΈ Adapters:
- Qs : strangerzonehf/Qs-Sketch
- Qd : strangerzonehf/Qd-Sketch
- Qx : strangerzonehf/Qx-Art
- Qc : strangerzonehf/Qc-Sketch
- Bb : strangerzonehf/Bg-Bag
π Collection : strangerzonehf/q-series-sketch-678e3503bf3a661758429717
πPage : https://huggingface.co./strangerzonehf
.
.
.
@prithivMLmods π€
reacted to
AdinaY's
post with π§
7 days ago
Post
2761
BIG release by DeepSeek AIπ₯π₯π₯
DeepSeek-R1 & DeepSeek-R1-Zero: two 660B reasoning models are here, alongside 6 distilled dense models (based on Llama & Qwen) for the community!
https://huggingface.co./deepseek-ai
deepseek-ai/DeepSeek-R1
β¨ MIT License : enabling distillation for custom models
β¨ 32B & 70B models match OpenAI o1-mini in multiple capabilities
β¨ API live now! Access Chain of Thought reasoning with model='deepseek-reasoner'
DeepSeek-R1 & DeepSeek-R1-Zero: two 660B reasoning models are here, alongside 6 distilled dense models (based on Llama & Qwen) for the community!
https://huggingface.co./deepseek-ai
deepseek-ai/DeepSeek-R1
β¨ MIT License : enabling distillation for custom models
β¨ 32B & 70B models match OpenAI o1-mini in multiple capabilities
β¨ API live now! Access Chain of Thought reasoning with model='deepseek-reasoner'
reacted to
as-cle-bert's
post with π₯
8 days ago
Post
1512
ππππ° πππ¦π¨ ππ₯ππ«ππ
Convert (almost) everything to PDF with πππππππ¨π°π§, now on Spaces! π as-cle-bert/pdfitdown
You can also install it locally:
Don't forget to star it on GitHub, if you find it useful! π https://www.github.com/AstraBert/PdfItDown
Convert (almost) everything to PDF with πππππππ¨π°π§, now on Spaces! π as-cle-bert/pdfitdown
You can also install it locally:
python3 -m pip install pdfitdownDon't forget to star it on GitHub, if you find it useful! π https://www.github.com/AstraBert/PdfItDown
-
- 3 replies
reacted to
mkurman's
post with π
10 days ago
Post
1228
ReasonFlow π§
Are you fascinated by reasoning models? If so, you won't want to miss my latest project! I've implemented multiple path generations to supercharge the reasoning capabilities of O1-like models. Explore how this work can elevate your model in complex reasoning tasks!
https://github.com/mkurman/ReasonFlow
Use it with:
mkurman/phi4-MedIT-10B-o1
- or -
mkurman/llama-3.2-MEDIT-3B-o1
Are you fascinated by reasoning models? If so, you won't want to miss my latest project! I've implemented multiple path generations to supercharge the reasoning capabilities of O1-like models. Explore how this work can elevate your model in complex reasoning tasks!
https://github.com/mkurman/ReasonFlow
Use it with:
mkurman/phi4-MedIT-10B-o1
- or -
mkurman/llama-3.2-MEDIT-3B-o1
- 1 reply
reacted to
merve's
post with β€οΈ
10 days ago
Post
2508
Everything that happened this week in open AI, a recap π€
merve/jan-17-releases-678a673a9de4a4675f215bf5
π Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance
π¬ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens π€―
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D π§π»ββοΈ
- ReaderLM-v2 is a new HTML parsing model by Jina AI
- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3
πΌοΈ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture
π£οΈ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities
π Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
π Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance
π¬ LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens π€―
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D π§π»ββοΈ
- ReaderLM-v2 is a new HTML parsing model by Jina AI
- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3
πΌοΈ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture
π£οΈ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities
π Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm
reacted to
hlarcher's
post with β€οΈ
11 days ago
Post
1055
We are introducing multi-backend support in Hugging Face Text Generation Inference!
With new TGI architecture we are now able to plug new modeling backends to get best performances according to selected model and available hardware. This first step will very soon be followed by the integration of new backends (TRT-LLM, llama.cpp, vLLM, Neuron and TPU).
We are polishing the TensorRT-LLM backend which achieves impressive performances on NVIDIA GPUs, stay tuned π€ !
Check out the details: https://huggingface.co./blog/tgi-multi-backend
With new TGI architecture we are now able to plug new modeling backends to get best performances according to selected model and available hardware. This first step will very soon be followed by the integration of new backends (TRT-LLM, llama.cpp, vLLM, Neuron and TPU).
We are polishing the TensorRT-LLM backend which achieves impressive performances on NVIDIA GPUs, stay tuned π€ !
Check out the details: https://huggingface.co./blog/tgi-multi-backend
posted
an
update
11 days ago
Post
2749
ChemQwen-vL [ Qwen for Chem Vision ] π§π»βπ¬
π§ͺModel : prithivMLmods/ChemQwen-vL
πChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format for chemical compounds and is optimized for chemical compound identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images. Its architecture operates within a multi-modal framework, combining image-text-text capabilities. It has been fine-tuned using datasets from: https://iupac.org/projects/
πColab Demo: https://tinyurl.com/2pn8x6u7, Collection : https://tinyurl.com/2mt5bjju
Inference with the documentation is possible with the help of the ReportLab library. https://pypi.org/project/reportlab/
π€: @prithivMLmods
π§ͺModel : prithivMLmods/ChemQwen-vL
πChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format for chemical compounds and is optimized for chemical compound identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images. Its architecture operates within a multi-modal framework, combining image-text-text capabilities. It has been fine-tuned using datasets from: https://iupac.org/projects/
πColab Demo: https://tinyurl.com/2pn8x6u7, Collection : https://tinyurl.com/2mt5bjju
Inference with the documentation is possible with the help of the ReportLab library. https://pypi.org/project/reportlab/
π€: @prithivMLmods
- 1 reply
reacted to
merve's
post with π₯
11 days ago
Post
1955
New smolagents example landed on Hugging Face cookbook π€
Learn how to create an inventory managing multi-agent system with smolagents, MongoDB and DeepSeek Chat π https://huggingface.co./learn/cookbook/mongodb_smolagents_multi_micro_agents
Learn how to create an inventory managing multi-agent system with smolagents, MongoDB and DeepSeek Chat π https://huggingface.co./learn/cookbook/mongodb_smolagents_multi_micro_agents
reacted to
davidberenstein1957's
post with π
13 days ago
Post
2094
π¦ What? The Hub as a vector search backend!
code: https://gist.github.com/davidberenstein1957/f0157a471ec59d9dd44ae6957f1d52ec
build on DuckDB: https://huggingface.co./docs/hub/en/datasets-duckdb
code: https://gist.github.com/davidberenstein1957/f0157a471ec59d9dd44ae6957f1d52ec
build on DuckDB: https://huggingface.co./docs/hub/en/datasets-duckdb
reacted to
hexgrad's
post with π₯
15 days ago
Post
18471
π£ Looking for labeled, high-quality synthetic audio/TTS data π£ 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. β€οΈ
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. β€οΈ
More details at hexgrad/Kokoro-82M#21
- 21 replies