deepseek-ai/DeepSeek-V3.2
Text Generation
•
685B
•
Updated
•
107k
•
•
1.04k
Makar Vlasov
Makar7
AI & ML interests
None yet
Recent Activity
liked
a model
21 days ago
deepseek-ai/DeepSeek-V3.2
liked
a model
21 days ago
deepseek-ai/DeepSeek-V3.2-Speciale
upvoted
a
collection
about 1 month ago
DeepSeek-Math
Organizations
None yet
liked
2
models
21 days ago
upvoted
a
collection
about 1 month ago
liked
2
models
about 1 month ago
liked
a
model
2 months ago
upvoted
a
collection
2 months ago
liked
a
model
2 months ago
liked
a
model
3 months ago
No results
#1 opened 3 months ago
by
Makar7
liked
a
model
3 months ago
Она всё же Алиса.
🤗
6
4
#4 opened 9 months ago
by
Makar7
reacted to
hannayukhymenko's
post with 👍
4 months ago
Post
2947
Releasing the Jupyter Agent Dataset! 🚀
Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.
We ( @baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.
Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset
Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.
We ( @baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.
Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset
- 3 replies
liked
a
Space
4 months ago
Release of Qwen image edit and controlnets?
6
#60 opened 5 months ago
by
krigeta
reacted to
MonsterMMORPG's
post with 🔥🚀
5 months ago
Post
3891
https://youtu.be/R6h02YY6gUs
Qwen Image is literally unchallenged at understanding complex prompts and writing amazing text on generated images. This model feels almost as if it’s illegal to be open source and free. It is my new tool for generating thumbnail images. Even with low-effort prompting, the results are excellent.
This tutorial literally shows how these images were generated with Gemini 2.5 Pro made prompts :
Qwen Image Dominates Text-to-Image: 700+ Tests Reveal Why It’s Better Than FLUX — Presets Published
https://youtu.be/R6h02YY6gUs
Gemini 2.5 Pro is freely available on Google Studio AI
All images generated in easy to use SwarmUI and they are unmodified raw generations
SwarmUI and ComfyUI install tutorial :
Master Local AI Art & Video Generation with SwarmUI (ComfyUI Backend): The Ultimate 2025 Tutorial
https://www.youtube.com/watch?v=fTzlQ0tjxj0
Qwen Image is literally unchallenged at understanding complex prompts and writing amazing text on generated images. This model feels almost as if it’s illegal to be open source and free. It is my new tool for generating thumbnail images. Even with low-effort prompting, the results are excellent.
This tutorial literally shows how these images were generated with Gemini 2.5 Pro made prompts :
Qwen Image Dominates Text-to-Image: 700+ Tests Reveal Why It’s Better Than FLUX — Presets Published
https://youtu.be/R6h02YY6gUs
Gemini 2.5 Pro is freely available on Google Studio AI
All images generated in easy to use SwarmUI and they are unmodified raw generations
SwarmUI and ComfyUI install tutorial :
Master Local AI Art & Video Generation with SwarmUI (ComfyUI Backend): The Ultimate 2025 Tutorial
https://www.youtube.com/watch?v=fTzlQ0tjxj0
reacted to
mitkox's
post with 🚀
5 months ago
Post
2119
I run Qwen3-Coder 480B locally on my Z8, with a 1-million token context window. It’s the equivalent of parallel-parking a Nimitz-class carrier in a kiddie pool. Thanks to whatever dark pact the llama.cpp, CUDA, and kernel folks signed, hybrid inferencing + VRAM↔RAM offload let me stream the model’s synapses across Xeon, RAM, and four lonely A6000s without summoning either the OOM killer or a small house fire.
liked
2
models
5 months ago
