Inference for PROs
β’
52
Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
liked
a model
24 minutes ago
NovaSky-AI/Sky-T1-32B-Preview
liked
a Space
about 18 hours ago
fffiloni/Sa2VA-simple-demo
liked
a Space
about 23 hours ago
declare-lab/TangoFlux
Articles
Organizations
victor's activity
Nice any hosted version?
reacted to
roseking's
post with π€
2 days ago
Post
1453
π Major Updates to HF Daily Paper Newsletter Bot
I'm excited to announce significant improvements to my HF Daily Paper Newsletter Bot! Here are the key updates:
πΌοΈ Enhanced Poster Generation
- Implemented dynamic height adjustment for daily paper posters
- Added support for displaying complete paper content without truncation
- Improved Chinese font rendering and text layout
- Integrated Hugging Face logo for better branding
- Enhanced visual aesthetics with optimized card layouts
π Content Improvements
- Removed paper count limitations (previously capped at 5 papers)
- Enhanced title and summary extraction algorithms
- Improved text wrapping and spacing for better readability
- Added proper handling of long content with automatic layout adjustments
π οΈ Technical Enhancements
- Implemented better font loading mechanism with fallback options
- Added support for multiple Chinese font paths
- Improved error handling and logging
- Enhanced memory management for image processing
- Added detailed debugging information
π Visual Design Updates
- Refined color scheme with HF brand colors
- Improved card spacing and padding
- Enhanced typography with better font sizing
- Added smooth transitions between paper cards
- Optimized overall layout for better visual hierarchy
π§ Infrastructure Updates
- Improved GitHub Actions workflow reliability
- Enhanced error notification system
- Added automatic retries for API calls
- Improved logging and debugging capabilities
The bot now generates more professional and visually appealing daily paper summaries while ensuring complete content display. These updates make the newsletter more readable and informative for our users.
Try it out and let me know what you think! Your feedback helps me make continuous improvements to better serve the AI research community.
#HuggingFace #AI #MachineLearning #ResearchPapers #OpenSource
I'm excited to announce significant improvements to my HF Daily Paper Newsletter Bot! Here are the key updates:
πΌοΈ Enhanced Poster Generation
- Implemented dynamic height adjustment for daily paper posters
- Added support for displaying complete paper content without truncation
- Improved Chinese font rendering and text layout
- Integrated Hugging Face logo for better branding
- Enhanced visual aesthetics with optimized card layouts
π Content Improvements
- Removed paper count limitations (previously capped at 5 papers)
- Enhanced title and summary extraction algorithms
- Improved text wrapping and spacing for better readability
- Added proper handling of long content with automatic layout adjustments
π οΈ Technical Enhancements
- Implemented better font loading mechanism with fallback options
- Added support for multiple Chinese font paths
- Improved error handling and logging
- Enhanced memory management for image processing
- Added detailed debugging information
π Visual Design Updates
- Refined color scheme with HF brand colors
- Improved card spacing and padding
- Enhanced typography with better font sizing
- Added smooth transitions between paper cards
- Optimized overall layout for better visual hierarchy
π§ Infrastructure Updates
- Improved GitHub Actions workflow reliability
- Enhanced error notification system
- Added automatic retries for API calls
- Improved logging and debugging capabilities
The bot now generates more professional and visually appealing daily paper summaries while ensuring complete content display. These updates make the newsletter more readable and informative for our users.
Try it out and let me know what you think! Your feedback helps me make continuous improvements to better serve the AI research community.
#HuggingFace #AI #MachineLearning #ResearchPapers #OpenSource
-
- 2 replies
reacted to
mitkox's
post with π₯
3 days ago
Post
2303
Can it run DeepSeek V3 671B is the new 'can it run Doom'.
How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.
Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.
Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.
Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
- 5 replies
reacted to
ngxson's
post with π
3 days ago
Post
1997
I made this small tool that can be useful for debugging Ollama chat template:
ngxson/ollama_template_test
CC @bartowski you may need this ;-)
CC @bartowski you may need this ;-)
- 2 replies
reacted to
jasoncorkill's
post with π
3 days ago
Post
1570
We had a few people asking about the differences and methodologies of our addition to the open-image-preferences dataset. So my colleague and I wrote a blog post about it with the new huggingface blog functionality: https://huggingface.co/blog/RapidataAI/more-image-preferences
reacted to
sequelbox's
post with π₯
3 days ago
Post
1311
NEW RELEASE: the
sequelbox/Tachibana-QVQ dataset is here! Code-reasoning and code-instruct data generated with
Qwen/QVQ-72B-Preview
Come check out QVQ's coding skills!
for everyone to use!
more QVQ and Llama 3.1 405b datasets coming soon :)
Come check out QVQ's coding skills!
for everyone to use!
more QVQ and Llama 3.1 405b datasets coming soon :)
reacted to
danielhanchen's
post with π₯
3 days ago
Post
2975
Deepseek V3, including GGUF + bf16 versions are now uploaded!
Includes 2, 3, 4, 5, 6 and 8-bit quantized versions.
GGUFs: unsloth/DeepSeek-V3-GGUF
bf16: unsloth/DeepSeek-V3-bf16
Min. hardware requirements to run: 48GB RAM + 250GB of disk space for 2-bit.
See how to run them with examples and the full collection: unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c
Includes 2, 3, 4, 5, 6 and 8-bit quantized versions.
GGUFs: unsloth/DeepSeek-V3-GGUF
bf16: unsloth/DeepSeek-V3-bf16
Min. hardware requirements to run: 48GB RAM + 250GB of disk space for 2-bit.
See how to run them with examples and the full collection: unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c
reacted to
reddgr's
post with π
3 days ago
Post
2244
Major update on the Talking to Chatbots dataset! Expanded the 'wrapped' dataset (one row per chat) to 2.86k records, and the 'unwrapped' version (one row per conversation turn) to 11k records. The main source is my ChatGPT archive with nearly 2 years of chats. It is still a work in progress as I incorporate chats from other sources and qualitative metrics (SCBN) for responses.
reddgr/talking-to-chatbots-unwrapped-chats
reddgr/talking-to-chatbots-chats
reddgr/talking-to-chatbots-unwrapped-chats
reddgr/talking-to-chatbots-chats
reacted to
prithivMLmods's
post with π
3 days ago
Post
5358
Reasoning SmolLM2 π
π―Fine-tuning SmolLM2 on a lightweight synthetic reasoning dataset for reasoning-specific tasks. Future updates will focus on lightweight, blazing-fast reasoning models. Until then, check out the blog for fine-tuning details.
π₯Blog : https://huggingface.co/blog/prithivMLmods/smollm2-ft
πΌ Models :
+ SmolLM2-CoT-360M : prithivMLmods/SmolLM2-CoT-360M
+ Reasoning-SmolLM2-135M : prithivMLmods/Reasoning-SmolLM2-135M
+ SmolLM2-CoT-360M-GGUF : prithivMLmods/SmolLM2-CoT-360M-GGUF
π€ Other Details :
+ Demo : prithivMLmods/SmolLM2-CoT-360M
+ Fine-tune nB : prithivMLmods/SmolLM2-CoT-360M
π―Fine-tuning SmolLM2 on a lightweight synthetic reasoning dataset for reasoning-specific tasks. Future updates will focus on lightweight, blazing-fast reasoning models. Until then, check out the blog for fine-tuning details.
π₯Blog : https://huggingface.co/blog/prithivMLmods/smollm2-ft
πΌ Models :
+ SmolLM2-CoT-360M : prithivMLmods/SmolLM2-CoT-360M
+ Reasoning-SmolLM2-135M : prithivMLmods/Reasoning-SmolLM2-135M
+ SmolLM2-CoT-360M-GGUF : prithivMLmods/SmolLM2-CoT-360M-GGUF
π€ Other Details :
+ Demo : prithivMLmods/SmolLM2-CoT-360M
+ Fine-tune nB : prithivMLmods/SmolLM2-CoT-360M
reacted to
hexgrad's
post with π₯
5 days ago
Post
4883
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
- 13 replies
reacted to
merve's
post with π₯
11 days ago
Post
4713
supercharge your LLM apps with smolagents π₯
however cool your LLM is, without being agentic it can only go so far
enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!
Here's our blog for you to get started https://huggingface.co/blog/smolagents
however cool your LLM is, without being agentic it can only go so far
enter smolagents: a new agent library by Hugging Face to make the LLM write code, do analysis and automate boring stuff!
Here's our blog for you to get started https://huggingface.co/blog/smolagents
reacted to
cfahlgren1's
post with π
11 days ago
Post
3296
The
deepseek-ai/DeepSeek-V3 is very good! I have been playing with it and found it is really good at one-shotting a pretty good landing page.
You can play with it here: https://deepseek-artifacts.vercel.app
All the responses get saved in the cfahlgren1/react-code-instructions dataset. Hopefully we can build one of the biggest, highest quality frontend datasets on the hub πͺ
You can play with it here: https://deepseek-artifacts.vercel.app
All the responses get saved in the cfahlgren1/react-code-instructions dataset. Hopefully we can build one of the biggest, highest quality frontend datasets on the hub πͺ
reacted to
sequelbox's
post with π
11 days ago
Post
2123
Check out the early preview of the upcoming Tachibana-QVQ dataset: code-reasoning and code-instruct data generated with
Qwen/QVQ-72B-Preview
Link here: sequelbox/Tachibana-QVQ-PREVIEW
more to come :)
Link here: sequelbox/Tachibana-QVQ-PREVIEW
more to come :)
- 1 reply
reacted to
ivanfioravanti's
post with π
13 days ago
Post
1542
Probably most of you already knows this trick but just in case:
π€ Unable to connect to Hugging Face Spaces Dev Mode through local Cursor? π‘ Don't worry there is an easy trick!
- right click Connect with VS Code
- copy link in your browser
- vscode://vscode-remote/...
- replace vscode with cursor and go
- cursor://vscode-remote/...
π€ Unable to connect to Hugging Face Spaces Dev Mode through local Cursor? π‘ Don't worry there is an easy trick!
- right click Connect with VS Code
- copy link in your browser
- vscode://vscode-remote/...
- replace vscode with cursor and go
- cursor://vscode-remote/...
reacted to
merve's
post with π
15 days ago
Post
4627
QwQ can see π₯
Qwen team released QvQ, a large vision LM with reasoning π±
it outperforms proprietary VLMs on several benchmarks, comes with open weights and a demo!
Check them out β¬οΈ
Demo Qwen/QVQ-72B-preview
Model Qwen/QVQ-72B-Preview
Read more https://qwenlm.github.io/blog/qvq-72b-preview/
Congratulations @JustinLin610 and team!
Qwen team released QvQ, a large vision LM with reasoning π±
it outperforms proprietary VLMs on several benchmarks, comes with open weights and a demo!
Check them out β¬οΈ
Demo Qwen/QVQ-72B-preview
Model Qwen/QVQ-72B-Preview
Read more https://qwenlm.github.io/blog/qvq-72b-preview/
Congratulations @JustinLin610 and team!
- 2 replies
reacted to
AdinaY's
post with ππ₯
15 days ago
Post
3577
The Chinese community is shipping π’
DeepSeek V3 (685 B MoE) has quietly released on the hub!
Base: deepseek-ai/DeepSeek-V3-Base
Instruct: deepseek-ai/DeepSeek-V3
Canβt wait to see whatβs next!
DeepSeek V3 (685 B MoE) has quietly released on the hub!
Base: deepseek-ai/DeepSeek-V3-Base
Instruct: deepseek-ai/DeepSeek-V3
Canβt wait to see whatβs next!
-
- 1 reply
reacted to
vincentg64's
post with π₯
15 days ago
Post
2220
LLM 2.0, RAG & Non-Standard Gen AI on GitHub https://mltblog.com/3DsyZSq
In this article, I share my latest Gen AI and LLM advances, featuring innovative approaches radically different from both standard AI and classical ML/NLP. The focus is on doing better with less, using efficient architectures, new algorithms and evaluation metrics. It originates from research that I started long ago. It gained significant momentum in the last two years. See background and history at https://mltblog.com/4g2sKTv.
OpenAI, Perplexity, Anthropic, Llama and others typically follow the trend and implement solutions very similar to mines within 3 to 6 months after I publish new milestones. For instance, multi-tokens, knowledge graph tokens, multi-indexes, real-time fine-tuning, mixtures of experts, LLM routers, small enterprise sub-LLMs, prompt distillation, relevancy scoring engine, deep contextual retrieval, optimum agentic chunking, and modern UI instead of the basic prompt box. I keep adding new features all the time, staying ahead of competition.
β‘οΈ Read full article with links to GitHub, at https://mltblog.com/3DsyZSq
In this article, I share my latest Gen AI and LLM advances, featuring innovative approaches radically different from both standard AI and classical ML/NLP. The focus is on doing better with less, using efficient architectures, new algorithms and evaluation metrics. It originates from research that I started long ago. It gained significant momentum in the last two years. See background and history at https://mltblog.com/4g2sKTv.
OpenAI, Perplexity, Anthropic, Llama and others typically follow the trend and implement solutions very similar to mines within 3 to 6 months after I publish new milestones. For instance, multi-tokens, knowledge graph tokens, multi-indexes, real-time fine-tuning, mixtures of experts, LLM routers, small enterprise sub-LLMs, prompt distillation, relevancy scoring engine, deep contextual retrieval, optimum agentic chunking, and modern UI instead of the basic prompt box. I keep adding new features all the time, staying ahead of competition.
β‘οΈ Read full article with links to GitHub, at https://mltblog.com/3DsyZSq
-
- 1 reply