lucasjin's picture

lucasjin

lucasjin

·

lucasjinreal

AI & ML interests

None yet

Recent Activity

updated a model 7 days ago

lucasjin/aimv2-4b-ve

new activity 11 days ago

HuggingFaceTB/SmolVLM-Instruct:How to training or fientunee SmolVLM easily?

updated a model 15 days ago

lucasjin/punc_ct-transformer_zh-cn-common-vocab272727-pytorch

View all activity

Organizations

lucasjin's activity

New activity in HuggingFaceTB/SmolVLM-Instruct 11 days ago

How to training or fientunee SmolVLM easily?

#21 opened 11 days ago by

New activity in CohereForAI/aya-expanse-8b about 2 months ago

ValueError: Tokenizer class CohereTokenizer does not exist or is not currently imported.

#9 opened about 2 months ago by

Chinese poetry is very bad

#10 opened about 2 months ago by

New activity in OpenGVLab/InternOmni 3 months ago

Multimodal model opensource

#1 opened 4 months ago by

New activity in CausalLM/miniG 4 months ago

Does there any tutorial on how to use the multimodal?

#8 opened 4 months ago by

New activity in Shakker-Labs/FLUX.1-dev-LoRA-Vector-Journey 4 months ago

Can it able to combine with a controlnet to edit existed photo foreground people to comic style?a

#1 opened 4 months ago by

New activity in omlab/omchat-v2.0-13B-single-beta_hf 4 months ago

is there any opensource repo for this?

#1 opened 4 months ago by

New activity in microsoft/Phi-3.5-MoE-instruct 4 months ago

About training mem usage for moe

#2 opened 4 months ago by

New activity in google/gemma-2-9b 5 months ago

Fine-tuning Hyperparameters

#27 opened 5 months ago by

New activity in microsoft/Florence-2-large-ft 5 months ago

Chinese very bad

#12 opened 6 months ago by

New activity in nyu-visionx/Cambrian-10M 5 months ago

data_engine image doesn't match question

#5 opened 6 months ago by

New activity in microsoft/Florence-2-large 5 months ago

How to retrain the model with large max length?

#46 opened 5 months ago by

New activity in nyu-visionx/Cambrian-10M 6 months ago

coco.tar.gz inside cocotrain2017 were lack of images

#6 opened 6 months ago by

New activity in microsoft/Florence-2-large 6 months ago

What does the output coordinate format?

#9 opened 6 months ago by

New activity in microsoft/Florence-2-large-ft 6 months ago

What is the prompt format for VQA?

#13 opened 6 months ago by

New activity in OpenGVLab/MVBench_Leaderboard 6 months ago

Sorry about miss upload

#5 opened 6 months ago by

New activity in OpenGVLab/InternVL2-26B 6 months ago

About the downsample ratio

#3 opened 6 months ago by

New activity in microsoft/Florence-2-large-ft 6 months ago

Swift now supports inference, training, and deployment of the Florence models.

#14 opened 6 months ago by

New activity in microsoft/Phi-3-small-8k-instruct 6 months ago

No triton for windows

#4 opened 7 months ago by

Why the inference speed so slow compare with same 7B parameters of Qwen?

#26 opened 6 months ago by