Peter Kis

NePe's activity

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

New activity in AlphaGaO/Qwen3-30B-A3B-GPTQ 4 months ago

Slow GPTQ inference

13

#1 opened 4 months ago by

NePe

New activity in JunHowie/Qwen3-30B-A3B-GPTQ-Int4 4 months ago

Slow GPTQ inference

5

#2 opened 4 months ago by

NePe

New activity in moonshotai/Moonlight-16B-A3B-Instruct 5 months ago

PEFT finetuning support

#14 opened 5 months ago by

NePe

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 6 months ago

Can't determine properly which is greater between 9.9 and 9.11

🧠 ➕ 2

10

#38 opened 6 months ago by

sniffski

New activity in google/gemma-2-27b-it about 1 year ago

with load_in_4bit it just generates <pad> tokens

2

#16 opened about 1 year ago by

NePe

New activity in rainjay/gemma-2-27b-it-4bit about 1 year ago

it just keeps generating <pad> tokens

3

#1 opened about 1 year ago by

NePe

New activity in TheBlokeAI/Mixtral-tiny-GPTQ over 1 year ago

Seems like the GPTQ versions are broken

4

#2 opened over 1 year ago by

NePe

What is this model?

3

#1 opened over 1 year ago by

Yuuru

New activity in TheBloke/Mixtral-8x7B-v0.1-GPTQ over 1 year ago

Build AutoGPTQ from source

3

#1 opened over 1 year ago by

PeePants

New activity in open-llm-leaderboard/open_llm_leaderboard almost 2 years ago

Impossible to search/filter for 13B GPTQ models.

9

#293 opened almost 2 years ago by

NePe

New activity in elinas/alpaca-30b-lora-int4 over 2 years ago

How to do inferance?

9

#2 opened over 2 years ago by

NePe

How to do inferance?

9

#2 opened over 2 years ago by

NePe

How to do inferance?

9

#2 opened over 2 years ago by

NePe