Prokhorov's picture

28 2 2

Prokhorov

Maverick17

·

AI & ML interests

None yet

Organizations

New activity in Qwen/Qwen3-30B-A3B 8 months ago

Waiting for the Qwen3-VL

#8 opened 8 months ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-dynamic-bnb-4bit 9 months ago

OOM on 2xH100

#3 opened 9 months ago by

New activity in AskUI/PTA-1 10 months ago

Dataset and hyperparameters for training

#3 opened 10 months ago by

New activity in osunlp/UGround-V1-Data 11 months ago

Null byte error

#2 opened 11 months ago by

New activity in OS-Copilot/OS-Atlas-Pro-7B about 1 year ago

How does the Agent is supposed to be working?

#2 opened about 1 year ago by

New activity in allenai/Molmo-7B-D-0924 about 1 year ago

Text -> Point -> Segmentation

#30 opened about 1 year ago by

New activity in showlab/ShowUI-2B about 1 year ago

Agent Loop

#6 opened about 1 year ago by

New activity in allenai/Molmo-7B-D-0924 about 1 year ago

How to finetune using DPO?

#31 opened about 1 year ago by

How should I extract attention maps? Can you provide a specific example?

#33 opened about 1 year ago by

Any plans on when vllm will be supported?

#26 opened about 1 year ago by

New activity in Maverick17/idefics3-llama-gui-dense-descriptions about 1 year ago

Using truncation in idefics3 processor

#1 opened about 1 year ago by

New activity in OpenGVLab/InternVL2-Llama3-76B over 1 year ago

Expected all tensors to be on the same device, but found at least two devices, cuda:2 and cuda:0!

#6 opened over 1 year ago by

New activity in HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 over 1 year ago

Token indices sequence length is longer than the specified maximum sequence length for this model (4645 > 2048)

#5 opened over 1 year ago by

New activity in utahnlp/robertabase-structured-tuning-srl-conll2012 over 2 years ago

Usage

#1 opened over 2 years ago by

Usage

#1 opened over 2 years ago by