Filipp

Regrin's activity

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

New activity in LiquidAI/LFM2.5-24B-A2B 12 days ago

Can you duplicate layers in this model?

2

#7 opened 12 days ago by

Regrin

New activity in JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF 14 days ago

Overthinking

5

#2 opened 15 days ago by

budkovsky

New activity in Qwen/Qwen3.8-27B 2 months ago

Best local model ever!

🤗 2

2

#137 opened 2 months ago by

ihshim523

New activity in google/gemma-4-12B-it 5 months ago

How to use an assistent model for MTP in llama.cpp?

2

#29 opened 5 months ago by

Regrin

Gemma 4:124b

👍🚀 91

18

#1 opened 5 months ago by

seamon67

New activity in recursal/QRWKV7-7B-Instruct 6 months ago

Can you convert Qwen 3.5 9b?

#3 opened 6 months ago by

Regrin

New activity in t-tech/T-pro-it-2.0 6 months ago

Можете обучить на том же датасете модель RWKV?

1

#6 opened 6 months ago by

Regrin

New activity in deepseek-ai/DeepSeek-V4-Pro 6 months ago

Is it uses engrams?

👀 3

2

#122 opened 6 months ago by

Regrin

New activity in featherless-ai/QRWKV-72B 6 months ago

Could you convert the Gemma 4 like this?

#6 opened 6 months ago by

Regrin

New activity in google/gemma-4-31B-it 6 months ago

Will there be a small model for speculative decoding?

3

#71 opened 6 months ago by

Regrin

Can anyone improve the model using the Rys methodology—by duplicating a block of layers?

11

#60 opened 7 months ago by

Regrin

Do Gemma 4 models work well?

3

#65 opened 6 months ago by

Regrin

New activity in google/gemma-4-31B-it 7 months ago

Gemma 4 E4B will be as encyclopedically well-read as the 12b model?

4

#48 opened 7 months ago by

Regrin

New activity in dnhkng/RYS-Qwen3.5-27B-FP8-XL 7 months ago

Can you improve the Gemma 4?

1

#2 opened 7 months ago by

Regrin

New activity in google/gemma-4-31B-it 7 months ago

Will there be QAT models?

🤝👍 12

4

#49 opened 7 months ago by

Regrin

How did you achieve such remarkable metrics?

🤝 2

7

#39 opened 7 months ago by

Regrin

New activity in VPTQ-community/README about 2 years ago

Can you start a Space with Qwen2.5 14b?

2

#2 opened about 2 years ago by

Regrin

Will this method of quantization appear in Ollama?

7

#1 opened about 2 years ago by

Regrin

New activity in mlabonne/FrankenLlama-3-12B-Instruct over 2 years ago

Сan you increase LLAMA3 8b simply by duplicating some layers?

3

#2 opened over 2 years ago by

Regrin