Article
Vision Language Models (Better, Faster, Stronger)
•
190
Dmitry Ryumin
DmitryRyumin
AI & ML interests
Machine Learning and Applications, Multi-Modal Understanding
Recent Activity
upvoted
an
article
about 15 hours ago
Vision Language Models (Better, Faster, Stronger)
liked
a Space
3 days ago
fffiloni/MimicMotion
liked
a model
5 days ago
nvidia/parakeet-tdt-0.6b-v2
Organizations
DmitryRyumin's activity
upvoted
an
article
about 15 hours ago
liked
a
Space
3 days ago
liked
a
model
5 days ago
liked
a
Space
5 days ago
liked
a
model
14 days ago
reacted to
merterbak's
post with 🔥
15 days ago
Post
4825
Qwen 3 models released🔥
It offers 2 MoE and 6 dense models with following parameter sizes: 0.6B, 1.7B, 4B, 8B, 14B, 30B(MoE), 32B, and 235B(MoE).
Models: Qwen/qwen3-67dd247413f0e2e4f653967f
Blog: https://qwenlm.github.io/blog/qwen3/
Demo: Qwen/Qwen3-Demo
GitHub: https://github.com/QwenLM/Qwen3
✅ Pre-trained 119 languages(36 trillion tokens) and dialects with strong translation and instruction following abilities. (Qwen2.5 was pre-trained on 18 trillion tokens.)
✅Qwen3 dense models match the performance of larger Qwen2.5 models. For example, Qwen3-1.7B/4B/8B/14B/32B perform like Qwen2.5-3B/7B/14B/32B/72B.
✅ Three stage done while pretraining:
• Stage 1: General language learning and knowledge building.
• Stage 2: Reasoning boost with STEM, coding, and logic skills.
• Stage 3: Long context training
✅ It supports MCP in the model
✅ Strong agent skills
✅ Supports seamless between thinking mode (for hard tasks like math and coding) and non-thinking mode (for fast chatting) inside chat template.
✅ Better human alignment for creative writing, roleplay, multi-turn conversations, and following detailed instructions.
It offers 2 MoE and 6 dense models with following parameter sizes: 0.6B, 1.7B, 4B, 8B, 14B, 30B(MoE), 32B, and 235B(MoE).
Models: Qwen/qwen3-67dd247413f0e2e4f653967f
Blog: https://qwenlm.github.io/blog/qwen3/
Demo: Qwen/Qwen3-Demo
GitHub: https://github.com/QwenLM/Qwen3
✅ Pre-trained 119 languages(36 trillion tokens) and dialects with strong translation and instruction following abilities. (Qwen2.5 was pre-trained on 18 trillion tokens.)
✅Qwen3 dense models match the performance of larger Qwen2.5 models. For example, Qwen3-1.7B/4B/8B/14B/32B perform like Qwen2.5-3B/7B/14B/32B/72B.
✅ Three stage done while pretraining:
• Stage 1: General language learning and knowledge building.
• Stage 2: Reasoning boost with STEM, coding, and logic skills.
• Stage 3: Long context training
✅ It supports MCP in the model
✅ Strong agent skills
✅ Supports seamless between thinking mode (for hard tasks like math and coding) and non-thinking mode (for fast chatting) inside chat template.
✅ Better human alignment for creative writing, roleplay, multi-turn conversations, and following detailed instructions.
upvoted
a
collection
15 days ago
liked
a
Space
15 days ago
upvoted
2
collections
15 days ago
liked
2
models
16 days ago
upvoted
a
collection
17 days ago
updated
a
Space
18 days ago
upvoted
an
article
19 days ago
Article
Welcome the Falcon 3 Family of Open Models!
•
127
liked
a
model
19 days ago
liked
a
Space
20 days ago
liked
a
Space
22 days ago
liked
a
model
22 days ago
updated
a
dataset
22 days ago