DedeProGames PRO

DedeProGames's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model about 5 hours ago

OrionLLM/Terminus-Qwen3-8b

Text Generation • 8B • Updated about 4 hours ago • 473 • 3

liked a model 1 day ago

OrionLLM/Terminus-LFM2.5-350m

Text Generation • 0.4B • Updated 1 day ago • 304 • 2

updated a collection 1 day ago

Terminus

Collection

Our research for small Terminal Agentic Models and Agentic datasets • 3 items • Updated about 5 hours ago • 1

updated a dataset 1 day ago

OrionLLM/OpenAgentInstruct

Viewer • Updated 1 day ago • 15.2k • 27 • 1

liked a model 1 day ago

mradermacher/model_requests

Updated Sep 11, 2025 • 157

New activity in mradermacher/model_requests 1 day ago

OrionLLM/Terminus-LFM2.5-350m

#2194 opened 1 day ago by

DedeProGames

updated a model 1 day ago

OrionLLM/Terminus-LFM2.5-350m

Text Generation • 0.4B • Updated 1 day ago • 304 • 2

published a model 1 day ago

OrionLLM/Terminus-LFM2.5-350m

Text Generation • 0.4B • Updated 1 day ago • 304 • 2

updated 2 models 1 day ago

OrionLLM/GRM-2.5

Image-Text-to-Text • 5B • Updated 1 day ago • 71 • 2

OrionLLM/GRM-2.5-Air

Image-Text-to-Text • 0.9B • Updated 1 day ago • 53 • 3

New activity in huggingface/InferenceSupport 1 day ago

OrionLLM/GRM-2.5-Air

🚀👀 1

#9204 opened 1 day ago by

DedeProGames

upvoted a collection 2 days ago

Terminus

Collection

Our research for small Terminal Agentic Models and Agentic datasets • 3 items • Updated about 5 hours ago • 1

updated a collection 2 days ago

Terminus

Collection

Our research for small Terminal Agentic Models and Agentic datasets • 3 items • Updated about 5 hours ago • 1

reactedto their post with 😎🧠👍 2 days ago

view post

Post

2950

🔥 GRM2 - The small one that surpasses the big ones.
What if a 3-parameter model can beat a 32-parameter model in every benchmark? We prove that it can.
GRM2 is a 3b params model based on the llama architecture, trained for long reasoning and high performance in complex tasks - the first 3b params model to outperform qwen3-32b in ALL benchmarks, and outperform o3-mini in almost all benchmarks.
🤗 Model: OrionLLM/GRM2-3b
The first 3b params model to generate over 1000 lines of code and achieve a score of 39.0 in xBench-DeepSearch-2510.

🚀 Chat with GRM:
DedeProGames/GRM2-Chat

🏆 Download official GGUFs: OrionLLM/GRM2-3b-GGUF

See translation

• 

🔥

6

6

👍

3

3

🤗

2

2

🤯

2

2

🧠

2

2

😎

2

2

+

Reply

upvoted a collection 2 days ago

Medical Research

Collection

Our research for medical models and datasets • 4 items • Updated 2 days ago • 1

updated a collection 2 days ago

Medical Research

Collection

Our research for medical models and datasets • 4 items • Updated 2 days ago • 1