Hugging Face's logo
DedeProGames's picture
In a Training Loop πŸ”„
44 10 72

DedeProGames PRO

DedeProGames
cahlen's profile picture HANAKT19's profile picture Zero-Point-AI's profile picture
Β·

AI & ML interests

Thinking and Agentic Finetuning

Recent Activity

upvoted a collection about 9 hours ago
Qwen3.5
reacted to theirpost with πŸ‘€ 1 day ago
πŸ”₯ GRM-2.5 - The most POWERFUL model for local inference The GRM-2.5 is the newest model from Orion LLM Labs. It has consistent RAW reasoning and is capable of generating very precise responses, similar to large models, while maintaining a parameter size of 4b. The GRM-2.5 family consists of these models: https://huggingface.co/OrionLLM/GRM-2.5 (4b) https://huggingface.co/OrionLLM/GRM-2.5-Air (0.8b) Furthermore, the GRM-2.5 is the best option for local agentic environments, being very good in code, terminal agent, etc. It is capable of generating 1000 lines of consistent code and programming like large models. The GRM-2.5 is the best base for FineTune to date and has vision, which means it can interpret images and videos.
reacted to theirpost with πŸ€— 1 day ago
πŸ”₯ GRM-2.5 - The most POWERFUL model for local inference The GRM-2.5 is the newest model from Orion LLM Labs. It has consistent RAW reasoning and is capable of generating very precise responses, similar to large models, while maintaining a parameter size of 4b. The GRM-2.5 family consists of these models: https://huggingface.co/OrionLLM/GRM-2.5 (4b) https://huggingface.co/OrionLLM/GRM-2.5-Air (0.8b) Furthermore, the GRM-2.5 is the best option for local agentic environments, being very good in code, terminal agent, etc. It is capable of generating 1000 lines of consistent code and programming like large models. The GRM-2.5 is the best base for FineTune to date and has vision, which means it can interpret images and videos.
View all activity

Organizations

Orion LLM Labs's profile picture