Filipp
Regrin
AI & ML interests
None yet
Recent Activity
new activity 22 minutes ago
google/gemma-4-12B-it:How to use an assistent model for MTP in llama.cpp? new activity 4 days ago
google/gemma-4-12B-it:Gemma 4:124b new activity about 1 month ago
recursal/QRWKV7-7B-Instruct:Can you convert Qwen 3.5 9b?Organizations
None yet
How to use an assistent model for MTP in llama.cpp?
#29 opened 22 minutes ago
by Regrin
Gemma 4:124b
👍🚀 88
18
#1 opened 4 days ago
by 
seamon67
Can you convert Qwen 3.5 9b?
#3 opened about 1 month ago
by Regrin
Можете обучить на том же датасете модель RWKV?
1
#6 opened about 1 month ago
by Regrin
Is it uses engrams?
👀 3
2
#122 opened about 1 month ago
by Regrin
Could you convert the Gemma 4 like this?
#6 opened about 2 months ago
by Regrin
Will there be a small model for speculative decoding?
3
#71 opened about 2 months ago
by Regrin
Can anyone improve the model using the Rys methodology—by duplicating a block of layers?
11
#60 opened about 2 months ago
by Regrin
Do Gemma 4 models work well?
3
#65 opened about 2 months ago
by Regrin
Gemma 4 E4B will be as encyclopedically well-read as the 12b model?
3
#48 opened about 2 months ago
by Regrin
Can you improve the Gemma 4?
1
#2 opened about 2 months ago
by Regrin
Will there be QAT models?
🤝👍 12
3
#49 opened about 2 months ago
by Regrin
How did you achieve such remarkable metrics?
🤝 2
6
#39 opened 2 months ago
by Regrin
Can you start a Space with Qwen2.5 14b?
2
#2 opened over 1 year ago
by Regrin
Will this method of quantization appear in Ollama?
7
#1 opened over 1 year ago
by Regrin
Сan you increase LLAMA3 8b simply by duplicating some layers?
3
#2 opened about 2 years ago
by Regrin