Hugging Face's logo
lucasjin's picture
112 3 199

lucasjin

lucasjin
clem's profile picture Michael3444's profile picture mathcrazyy's profile picture
·

AI & ML interests

None yet

Organizations

OpenBuddy Community's profile picture Stable Diffusion Community (Unofficial, Non-profit)'s profile picture

lucasjin's activity

New activity in OpenGVLab/InternOmni 8 days ago

Multimodal model opensource

1
#1 opened 24 days ago by YangJiassh
New activity in CausalLM/miniG 19 days ago

Does there any tutorial on how to use the multimodal?

3
#8 opened 21 days ago by lucasjin
New activity in omlab/omchat-v2.0-13B-single-beta_hf 27 days ago

is there any opensource repo for this?

3
#1 opened about 1 month ago by lucasjin
New activity in microsoft/Phi-3.5-MoE-instruct about 1 month ago

About training mem usage for moe

3
#2 opened about 1 month ago by lucasjin
New activity in google/gemma-2-9b about 2 months ago

Fine-tuning Hyperparameters

6
#27 opened 2 months ago by tanliboy
New activity in microsoft/Florence-2-large-ft 2 months ago

Chinese very bad

14
#12 opened 3 months ago by lucasjin
New activity in nyu-visionx/Cambrian-10M 2 months ago

data_engine image doesn't match question

3
#5 opened 2 months ago by NightStar
New activity in microsoft/Florence-2-large 2 months ago

How to retrain the model with large max length?

5
#46 opened 2 months ago by lucasjin
New activity in nyu-visionx/Cambrian-10M 2 months ago

coco.tar.gz inside cocotrain2017 were lack of images
#6 opened 2 months ago by lucasjin
New activity in microsoft/Florence-2-large 2 months ago

What does the output coordinate format?

6
#9 opened 3 months ago by lucasjin
New activity in microsoft/Florence-2-large-ft 3 months ago

What is the prompt format for VQA?

4
#13 opened 3 months ago by dnhkng
New activity in OpenGVLab/MVBench_Leaderboard 3 months ago

Sorry about miss upload
#5 opened 3 months ago by lucasjin
New activity in OpenGVLab/InternVL2-26B 3 months ago

About the downsample ratio

2
#3 opened 3 months ago by lucasjin
New activity in microsoft/Florence-2-large-ft 3 months ago

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

3
#14 opened 3 months ago by hu5enpai
New activity in microsoft/Phi-3-small-8k-instruct 3 months ago

No triton for windows

2
#4 opened 4 months ago by fernandomir

Why the inference speed so slow compare with same 7B parameters of Qwen?
#26 opened 3 months ago by lucasjin
New activity in nyu-visionx/cambrian-phi3-3b 3 months ago

How's the result?

1
#1 opened 3 months ago by lucasjin
New activity in microsoft/Phi-3-small-128k-instruct 3 months ago

Does it support system?
#22 opened 3 months ago by lucasjin
New activity in microsoft/Florence-2-large 3 months ago

How to increase max token output ?

1
#40 opened 3 months ago by Truc95
New activity in OpenGVLab/MVBench 3 months ago

Fine-grained Action lost

3
#3 opened 7 months ago by xmy0916
New activity in microsoft/Florence-2-large 3 months ago

Question about continue pretrain on Florence large base model with more data

2
#30 opened 3 months ago by lucasjin
commented a paper 3 months ago
New activity in OpenGVLab/MVBench 3 months ago

video/star/Charades_v1_480/EDXBD.mp4 Not found

3
#4 opened 3 months ago by lucasjin
New activity in fun-research/TiTok 3 months ago

Please release the code

1
#1 opened 3 months ago by lucasjin
commented a paper 3 months ago
New activity in OpenGVLab/ShareGPT-4o 4 months ago

Suggestion: add source of the images.

2
#3 opened 4 months ago by lucasjin
New activity in THUDM/chatglm2-6b 4 months ago

fix modeling_chatglm.py error: `-` operator, with a bool tensor is not supported

1
#67 opened about 1 year ago by shibing624
New activity in THUDM/glm-4v-9b 4 months ago

Can not inference

1
#4 opened 4 months ago by lucasjin

观察到vision特征的最后除了一个数值为8的scaling

1
#2 opened 4 months ago by xiechunyu
New activity in OpenGVLab/InternViT-300M-448px 4 months ago

The result is not good as Siglip

1
#1 opened 4 months ago by lucasjin
New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit 4 months ago

When will transformers' s siglip supports FlashAtten?

2
#5 opened 4 months ago by lucasjin
New activity in HuggingFaceM4/idefics2-8b 4 months ago

How does the attention_mask contribute to the projector preformance?

12
#45 opened 5 months ago by lucasjin
New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit 4 months ago

What processor to use?

9
#4 opened 5 months ago by floschne
New activity in HuggingFaceM4/idefics2-8b 4 months ago

Bug in attention mask

1
#58 opened 4 months ago by lucasjin
New activity in 01-ai/Yi-1.5-9B-Chat 4 months ago

V100 32GB can not inference

1
#3 opened 4 months ago by lucasjin
New activity in Nexdata/1297_Images_Chinese_Handwriting_OCR_Data 5 months ago

SPan
#1 opened 5 months ago by lucasjin
New activity in unsloth/llama-3-8b 5 months ago

is this the llama-3-8b model clone?

13
#1 opened 5 months ago by malhajar
New activity in HuggingFaceM4/idefics2-8b 5 months ago

About the token / per image in report

2
#13 opened 5 months ago by lucasjin

Where is source code?

1
#12 opened 5 months ago by lucasjin
New activity in apple/DFN5B-CLIP-ViT-H-14-378 5 months ago

The performance is very bad
#2 opened 5 months ago by lucasjin
New activity in jetmoe/jetmoe-8b-chat 6 months ago

What's the chat template used here?

3
#1 opened 6 months ago by lucasjin
New activity in laion/gpt4v-dataset 6 months ago

How to download the images?
#25 opened 6 months ago by lucasjin
New activity in OpenGVLab/InternVL-Chat-V1-2 7 months ago

GeoQA+ missing images

3
#5 opened 7 months ago by lucasjin
New activity in Mizukiluke/ureader-instruction-1.0 8 months ago

Many assistant response are None.
#2 opened 8 months ago by lucasjin
New activity in HuggingFaceM4/LLaVAR-Instruct-16K 8 months ago

Does the pretrain data open?

1
#1 opened 8 months ago by lucasjin
New activity in openbmb/MiniCPM-2B-sft-fp32 8 months ago

Why a 2B model size up to 80% of 7B?

1
#2 opened 8 months ago by lucasjin
New activity in gradio/image_mod 8 months ago

I didn't say how does clear and sublimt claimed in code?
#2 opened 8 months ago by lucasjin
New activity in 01-ai/Yi-VL-34B 8 months ago

Can't load model&inference with LLava's latest inference code

3
#3 opened 8 months ago by kldsaid

Unable to load

1
#4 opened 8 months ago by lucasjin

Int4 version maybe?

2
#2 opened 8 months ago by lucasjin
New activity in TheBloke/DiscoLM_German_7b_v1-AWQ 8 months ago

yi-34B VL's int4 please
#1 opened 8 months ago by lucasjin
New activity in cloudyu/Mixtral_34Bx2_MoE_60B 9 months ago

source code and paper?

8
#6 opened 9 months ago by josephykwang
New activity in cloudyu/Yi-34Bx2-MoE-60B 9 months ago

is this base model or sft model?

1
#3 opened 9 months ago by lucasjin
New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b 9 months ago

Add some multi language data

1
#10 opened 9 months ago by lucasjin
New activity in OedoSoldier/Bert-VITS2-2.2-CLAP 9 months ago

RuntimeError: min(): Expected reduction dim to be specified for input.numel() == 0. Specify the reduction dim with the 'dim' argument.

1
#2 opened 9 months ago by lucasjin
New activity in diffusers/stable-diffusion-xl-1.0-inpainting-0.1 9 months ago

Is there a combined model?
#16 opened 9 months ago by lucasjin
New activity in fblgit/una-xaberius-34b-v1beta 10 months ago

Compare with official Yi-34B-Chat?

5
#6 opened 10 months ago by lucasjin
New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 10 months ago

Nevermind. This was probably an Arc test issue.

2
#7 opened 10 months ago by deleted
New activity in diffusers/stable-diffusion-xl-1.0-inpainting-0.1 10 months ago

Use in ComfyUI?

5
#9 opened about 1 year ago by eyesss

the inpainted result seems blury, why?

2
#13 opened 11 months ago by lvZic