deepseek-ai/DeepSeek-V3-0324
Text Generation
•
Updated
•
20.1k
•
•
1.61k
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
liked
a model
about 22 hours ago
deepseek-ai/DeepSeek-V3-0324
liked
a model
about 22 hours ago
DevQuasar/analytical_reasoning_r16a32_unsloth-Llama-3.2-3B-Instruct-bnb-4bit
Organizations
AtAndDev's activity
liked
2
models
about 22 hours ago
reacted to
openfree's
post with ❤️👀🚀🔥
about 22 hours ago
Post
2928
🚀 DeepSeek V3-0324 + Real-time Research Power! 🌐
Hello there! Today I'm excited to introduce an amazing tool based on the DeepSeek V3-0324 latest model. This isn't just another AI chatbot—it's a true "research assistant" capable of real-time information retrieval and analysis!
openfree/Deepseek-v3-0324-Research
🧠 Key Strengths of DeepSeek V3-0324
DeepSeek V3-0324, provided by Fireworks AI, comes with these powerful advantages:
🎯 Superior Reasoning: Excellent ability to solve complex problems step-by-step
📚 Extensive Knowledge: Deep understanding across various topics from comprehensive training
🧩 Context Awareness: Maintains long conversation contexts for consistent responses
🌍 Multilingual Support: Processes various languages effectively
🔎 Added Real-time "Deep Research" Capability!
The most exciting feature of this project is the implementation of real-time search functionality similar to ChatGPT's Browse with Bing or Perplexity AI! 🌟
How does it work?
📋 Query Analysis: Analyzes questions to automatically extract optimal search keywords
🌐 Web Search: Utilizes advanced search technology to retrieve the latest information
🧪 Result Analysis: Intelligently analyzes search results and evaluates relevance
💡 Comprehensive Response: Combines freshly retrieved information with AI's existing knowledge
Key Benefits:
⏱️ Up-to-date Information: Always provides the latest data through real-time web searches
📊 Enhanced Reliability: Improves trustworthiness by citing information sources
🔄 Overcoming Knowledge Limitations: Handles questions beyond the AI's training cutoff
🛠️ Research Efficiency: Processes everything from information retrieval to analysis in one go
🖥️ How to Use
It's simple! Just enable the "Deep Research" checkbox and ask your question. The AI will automatically search for and analyze relevant information to provide rich, informed answers.
Hello there! Today I'm excited to introduce an amazing tool based on the DeepSeek V3-0324 latest model. This isn't just another AI chatbot—it's a true "research assistant" capable of real-time information retrieval and analysis!
openfree/Deepseek-v3-0324-Research
🧠 Key Strengths of DeepSeek V3-0324
DeepSeek V3-0324, provided by Fireworks AI, comes with these powerful advantages:
🎯 Superior Reasoning: Excellent ability to solve complex problems step-by-step
📚 Extensive Knowledge: Deep understanding across various topics from comprehensive training
🧩 Context Awareness: Maintains long conversation contexts for consistent responses
🌍 Multilingual Support: Processes various languages effectively
🔎 Added Real-time "Deep Research" Capability!
The most exciting feature of this project is the implementation of real-time search functionality similar to ChatGPT's Browse with Bing or Perplexity AI! 🌟
How does it work?
📋 Query Analysis: Analyzes questions to automatically extract optimal search keywords
🌐 Web Search: Utilizes advanced search technology to retrieve the latest information
🧪 Result Analysis: Intelligently analyzes search results and evaluates relevance
💡 Comprehensive Response: Combines freshly retrieved information with AI's existing knowledge
Key Benefits:
⏱️ Up-to-date Information: Always provides the latest data through real-time web searches
📊 Enhanced Reliability: Improves trustworthiness by citing information sources
🔄 Overcoming Knowledge Limitations: Handles questions beyond the AI's training cutoff
🛠️ Research Efficiency: Processes everything from information retrieval to analysis in one go
🖥️ How to Use
It's simple! Just enable the "Deep Research" checkbox and ask your question. The AI will automatically search for and analyze relevant information to provide rich, informed answers.
- 1 reply
liked
a
model
1 day ago
reacted to
merve's
post with 🤗
3 days ago
Post
3013
So many open releases at Hugging Face past week 🤯 recapping all here ⤵️
merve/march-21-releases-67dbe10e185f199e656140ae
👀 Multimodal
> Mistral AI released a 24B vision LM, both base and instruction FT versions, sota 🔥 (OS)
> with IBM we released SmolDocling, a sota 256M document parser with Apache 2.0 license (OS)
> SpatialLM is a new vision LM that outputs 3D bounding boxes, comes with 0.5B (QwenVL based) and 1B (Llama based) variants
> SkyWork released SkyWork-R1V-38B, new vision reasoning model (OS)
💬 LLMs
> NVIDIA released new Nemotron models in 49B and 8B with their post-training dataset
> LG released EXAONE, new reasoning models in 2.4B, 7.8B and 32B
> Dataset: Glaive AI released a new reasoning dataset of 22M+ examples
> Dataset: NVIDIA released new helpfulness dataset HelpSteer3
> Dataset: OpenManusRL is a new agent dataset based on ReAct framework (OS)
> Open-R1 team released OlympicCoder, new competitive coder model in 7B and 32B
> Dataset: GeneralThought-430K is a new reasoning dataset (OS)
🖼️ Image Generation/Computer Vision
> Roboflow released RF-DETR, new real-time sota object detector (OS) 🔥
> YOLOE is a new real-time zero-shot object detector with text and visual prompts 🥹
> Stability AI released Stable Virtual Camera, a new novel view synthesis model
> Tencent released Hunyuan3D-2mini, new small and fast 3D asset generation model
> ByteDance released InfiniteYou, new realistic photo generation model
> StarVector is a new 8B model that generates svg from images
> FlexWorld is a new model that expands 3D views (OS)
🎤 Audio
> Sesame released CSM-1B new speech generation model (OS)
🤖 Robotics
> NVIDIA released GR00T, new robotics model for generalized reasoning and skills, along with the dataset
*OS ones have Apache 2.0 or MIT license
👀 Multimodal
> Mistral AI released a 24B vision LM, both base and instruction FT versions, sota 🔥 (OS)
> with IBM we released SmolDocling, a sota 256M document parser with Apache 2.0 license (OS)
> SpatialLM is a new vision LM that outputs 3D bounding boxes, comes with 0.5B (QwenVL based) and 1B (Llama based) variants
> SkyWork released SkyWork-R1V-38B, new vision reasoning model (OS)
💬 LLMs
> NVIDIA released new Nemotron models in 49B and 8B with their post-training dataset
> LG released EXAONE, new reasoning models in 2.4B, 7.8B and 32B
> Dataset: Glaive AI released a new reasoning dataset of 22M+ examples
> Dataset: NVIDIA released new helpfulness dataset HelpSteer3
> Dataset: OpenManusRL is a new agent dataset based on ReAct framework (OS)
> Open-R1 team released OlympicCoder, new competitive coder model in 7B and 32B
> Dataset: GeneralThought-430K is a new reasoning dataset (OS)
🖼️ Image Generation/Computer Vision
> Roboflow released RF-DETR, new real-time sota object detector (OS) 🔥
> YOLOE is a new real-time zero-shot object detector with text and visual prompts 🥹
> Stability AI released Stable Virtual Camera, a new novel view synthesis model
> Tencent released Hunyuan3D-2mini, new small and fast 3D asset generation model
> ByteDance released InfiniteYou, new realistic photo generation model
> StarVector is a new 8B model that generates svg from images
> FlexWorld is a new model that expands 3D views (OS)
🎤 Audio
> Sesame released CSM-1B new speech generation model (OS)
🤖 Robotics
> NVIDIA released GR00T, new robotics model for generalized reasoning and skills, along with the dataset
*OS ones have Apache 2.0 or MIT license
reacted to
Jaward's
post with 🔥
3 days ago
Post
3532
Implemented a custom multimodal GRPO trainer that scales for Small VLMs, supports cpu and gpu with vllm + flash attention. Using SmolVLM-256M-Instruct reference & reward model, wasn’t trained for long btw, still got some sparks of “thinking”:)
Code: https://github.com/Jaykef/ai-algorithms/blob/main/grpo_multimodal_reasoner.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/grpo_multimodal_reasoner.ipynb
- 1 reply
replied to
MonsterMMORPG's
post
5 days ago
I didnt mean you lul
I meant him
@MonsterMMORPG
...
replied to
MonsterMMORPG's
post
6 days ago
brother, dunking on some great models to defend your "product" is not a great (hate to say it but) human value...
replied to
nroggendorff's
post
6 days ago
ma guys suffered ik :)
reacted to
onekq's
post with 😔
6 days ago
Post
1545
I like to benchmark 💵o1-pro💵 but it is way too expensive for me 🤦♂️
-
- 4 replies
Its expensive for everyone, just go with o3-mini, they just figured out that they are not the single llm provider and just doubled the cost of r1 for o3-mini.
reacted to
etemiz's
post with 🚀😎👀
6 days ago
Post
1668
Started fine tuning Gemma 3 using evolutionary approach. It is not the worst model according to AHA leaderboard and it is one of the smart according to lmarena.ai. My objective is to make it based, anti woke, wise, beneficial and then some.
Several GPUs are fine tuning it at the same time, each using a different dataset and using QLoRA and the successful ones are merged later. Compared to LoRa this allows faster training and also reduced overfitting because the merge operation heals overfitting. The problem with this could be the 4 bit quantization may make models dumber. But I am not looking for sheer IQ. Too much mind is a problem anyway :)
Has anyone tried parallel QLoRa and merge before?
I also automated the dataset selection and benchmarking and converging to objectives (the fit function, the reward). It is basically trying to get higher score in AHA Leaderboard as fast as possible with a diverse set of organisms that "evolve by training".
I want to release some cool stuff when I have the time:
- how an answer to a single question changes over time, with each training round or day
- a chart to show AHA alignment over training rounds
Several GPUs are fine tuning it at the same time, each using a different dataset and using QLoRA and the successful ones are merged later. Compared to LoRa this allows faster training and also reduced overfitting because the merge operation heals overfitting. The problem with this could be the 4 bit quantization may make models dumber. But I am not looking for sheer IQ. Too much mind is a problem anyway :)
Has anyone tried parallel QLoRa and merge before?
I also automated the dataset selection and benchmarking and converging to objectives (the fit function, the reward). It is basically trying to get higher score in AHA Leaderboard as fast as possible with a diverse set of organisms that "evolve by training".
I want to release some cool stuff when I have the time:
- how an answer to a single question changes over time, with each training round or day
- a chart to show AHA alignment over training rounds
- 3 replies
liked
a
model
6 days ago
reacted to
clem's
post with 👀
6 days ago
Post
3595
Should we assemble affordable open-source robots at Hugging Face for the community. Would you buy them? At what price?
- 8 replies
upvoted
a
paper
6 days ago