Filipp

Regrin's activity

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

New activity in recursal/QRWKV7-7B-Instruct 23 days ago

Can you convert Qwen 3.5 9b?

#3 opened 23 days ago by

Regrin

New activity in t-tech/T-pro-it-2.0 25 days ago

Можете обучить на том же датасете модель RWKV?

1

#6 opened 25 days ago by

Regrin

New activity in deepseek-ai/DeepSeek-V4-Pro about 1 month ago

Is it uses engrams?

👀 3

2

#122 opened about 1 month ago by

Regrin

New activity in featherless-ai/QRWKV-72B about 1 month ago

Could you convert the Gemma 4 like this?

#6 opened about 1 month ago by

Regrin

New activity in google/gemma-4-31B-it about 1 month ago

Will there be a small model for speculative decoding?

3

#71 opened about 1 month ago by

Regrin

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

11

#60 opened about 1 month ago by

Regrin

Do Gemma 4 models work well?

3

#65 opened about 1 month ago by

Regrin

New activity in google/gemma-4-31B-it about 2 months ago

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

3

#48 opened about 2 months ago by

Regrin

New activity in dnhkng/RYS-Qwen3.5-27B-FP8-XL about 2 months ago

Can you improve the Gemma 4?

1

#2 opened about 2 months ago by

Regrin

New activity in google/gemma-4-31B-it about 2 months ago

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 about 2 months ago by

Regrin

New activity in VPTQ-community/README over 1 year ago

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

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

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

3

#2 opened about 2 years ago by

Regrin