Peter Kis's picture

Peter Kis

NePe

·

AI & ML interests

None yet

Recent Activity

new activity 8 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5:variable_cache.py compatibility for v4.57.2 / python3.12

new activity 8 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5:Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced `NEED_SETUP_CACHE_CLASSES_MAPPING`

new activity 13 days ago

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5:cannot import name 'NEED_SETUP_CACHE_CLASSES_MAPPING'

View all activity

Organizations

New activity in nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 8 days ago

variable_cache.py compatibility for v4.57.2 / python3.12

#12 opened 13 days ago by

Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced `NEED_SETUP_CACHE_CLASSES_MAPPING`

#9 opened 29 days ago by

New activity in nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 13 days ago

cannot import name 'NEED_SETUP_CACHE_CLASSES_MAPPING'

#11 opened 14 days ago by

New activity in AlphaGaO/Qwen3-30B-A3B-GPTQ 7 months ago

Slow GPTQ inference

#1 opened 7 months ago by

New activity in JunHowie/Qwen3-30B-A3B-GPTQ-Int4 7 months ago

Slow GPTQ inference

#2 opened 7 months ago by

New activity in moonshotai/Moonlight-16B-A3B-Instruct 8 months ago

PEFT finetuning support

#14 opened 8 months ago by

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 9 months ago

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

#38 opened 9 months ago by

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

with load_in_4bit it just generates <pad> tokens

#16 opened over 1 year ago by

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

it just keeps generating <pad> tokens

#1 opened over 1 year ago by

New activity in TheBlokeAI/Mixtral-tiny-GPTQ almost 2 years ago

Seems like the GPTQ versions are broken

#2 opened almost 2 years ago by

What is this model?

#1 opened almost 2 years ago by

New activity in TheBloke/Mixtral-8x7B-v0.1-GPTQ almost 2 years ago

Build AutoGPTQ from source

#1 opened almost 2 years ago by

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

Impossible to search/filter for 13B GPTQ models.

#293 opened about 2 years ago by

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

How to do inferance?

#2 opened over 2 years ago by

How to do inferance?

#2 opened over 2 years ago by

How to do inferance?

#2 opened over 2 years ago by