lucasjin

New activity in OpenGVLab/InternVL2-26B about 17 hours ago

About the downsample ratio

#3 opened about 17 hours ago by

New activity in microsoft/Florence-2-large-ft 4 days ago

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

#14 opened 9 days ago by

hu5enpai

New activity in microsoft/Phi-3-small-8k-instruct 4 days ago

No triton for windows

#4 opened about 2 months ago by

fernandomir

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

#26 opened 4 days ago by

New activity in nyu-visionx/cambrian-phi3-3b 4 days ago

How's the result?

#1 opened 4 days ago by

New activity in microsoft/Phi-3-small-128k-instruct 4 days ago

Does it support system?

#22 opened 4 days ago by

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

How to increase max token output ?

#40 opened 5 days ago by

Truc95

New activity in OpenGVLab/MVBench 6 days ago

Fine-grained Action lost

#3 opened 4 months ago by

xmy0916

New activity in microsoft/Florence-2-large 7 days ago

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

#30 opened 10 days ago by

Paper • 2406.07550 • Published 26 days ago • 53 •

commented a paper 14 days ago

An Image is Worth 32 Tokens for Reconstruction and Generation

20

New activity in OpenGVLab/MVBench 14 days ago

video/star/Charades_v1_480/EDXBD.mp4 Not found

#4 opened 14 days ago by

New activity in fun-research/TiTok 16 days ago

Please release the code

#1 opened 16 days ago by

Paper • 2406.12275 • Published 20 days ago • 28 •

commented a paper 16 days ago

VoCo-LLaMA: Towards Vision Compression with Large Language Models

10

New activity in microsoft/Florence-2-large 16 days ago

What does the output coordinate format?

#9 opened 17 days ago by

New activity in OpenGVLab/ShareGPT-4o about 1 month ago

Suggestion: add source of the images.

#3 opened about 1 month ago by

New activity in THUDM/chatglm2-6b about 1 month ago

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

#67 opened 12 months ago by

shibing624

New activity in THUDM/glm-4v-9b about 1 month ago

Can not inference

#4 opened about 1 month ago by

观察到vision特征的最后除了一个数值为8的scaling

#2 opened about 1 month ago by

xiechunyu

New activity in OpenGVLab/InternViT-300M-448px about 1 month ago

The result is not good as Siglip

#1 opened about 1 month ago by

New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit about 1 month ago

When will transformers' s siglip supports FlashAtten?

#5 opened about 1 month ago by

New activity in HuggingFaceM4/idefics2-8b about 1 month ago

How does the attention_mask contribute to the projector preformance?

12

#45 opened about 2 months ago by

New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit about 2 months ago

What processor to use?

9

#4 opened 2 months ago by

floschne

New activity in HuggingFaceM4/idefics2-8b about 2 months ago

Bug in attention mask

#58 opened about 2 months ago by

New activity in 01-ai/Yi-1.5-9B-Chat about 2 months ago

V100 32GB can not inference

#3 opened about 2 months ago by

New activity in Nexdata/1297_Images_Chinese_Handwriting_OCR_Data 2 months ago

SPan

#1 opened 2 months ago by

New activity in unsloth/llama-3-8b 3 months ago

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

13

#1 opened 3 months ago by

malhajar

New activity in HuggingFaceM4/idefics2-8b 3 months ago

About the token / per image in report

#13 opened 3 months ago by

Where is source code?

#12 opened 3 months ago by

New activity in apple/DFN5B-CLIP-ViT-H-14-378 3 months ago

The performance is very bad

#2 opened 3 months ago by

New activity in jetmoe/jetmoe-8b-chat 3 months ago

What's the chat template used here?

#1 opened 3 months ago by

New activity in laion/gpt4v-dataset 3 months ago

How to download the images?

#25 opened 3 months ago by

New activity in OpenGVLab/InternVL-Chat-V1-2 5 months ago

GeoQA+ missing images

#5 opened 5 months ago by

New activity in Mizukiluke/ureader-instruction-1.0 5 months ago

Many assistant response are None.

#2 opened 5 months ago by

New activity in HuggingFaceM4/LLaVAR-Instruct-16K 5 months ago

Does the pretrain data open?

#1 opened 5 months ago by

New activity in openbmb/MiniCPM-2B-sft-fp32 5 months ago

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

#2 opened 5 months ago by

New activity in gradio/image_mod 5 months ago

I didn't say how does clear and sublimt claimed in code?

#2 opened 5 months ago by

New activity in 01-ai/Yi-VL-34B 6 months ago

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

#3 opened 6 months ago by

kldsaid

Unable to load

#4 opened 6 months ago by

Int4 version maybe?

#2 opened 6 months ago by

New activity in TheBloke/DiscoLM_German_7b_v1-AWQ 6 months ago

yi-34B VL's int4 please

#1 opened 6 months ago by

New activity in cloudyu/Mixtral_34Bx2_MoE_60B 6 months ago

source code and paper?

8

#6 opened 6 months ago by

josephykwang

New activity in cloudyu/Yi-34Bx2-MoE-60B 6 months ago

is this base model or sft model?

#3 opened 6 months ago by

New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b 7 months ago

Add some multi language data

#10 opened 7 months ago by

New activity in OedoSoldier/Bert-VITS2-2.2-CLAP 7 months ago

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

#2 opened 7 months ago by

New activity in diffusers/stable-diffusion-xl-1.0-inpainting-0.1 7 months ago

Is there a combined model?

#16 opened 7 months ago by

New activity in fblgit/una-xaberius-34b-v1beta 7 months ago

Compare with official Yi-34B-Chat?

5

#6 opened 7 months ago by

New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 7 months ago

Nevermind. This was probably an Arc test issue.

#7 opened 7 months ago by deleted

New activity in diffusers/stable-diffusion-xl-1.0-inpainting-0.1 7 months ago

Use in ComfyUI?

5

#9 opened 10 months ago by

eyesss

the inpainted result seems blury, why?

#13 opened 9 months ago by

lvZic

the inpainting result by this repo is false, the resolution degrade and noise increase!

#15 opened 8 months ago by

lvZic

New activity in stabilityai/stable-diffusion-xl-refiner-0.9 7 months ago

sd xl refiner for 1.0 version

#15 opened 7 months ago by

New activity in zgce/acsr-v2-yi34b-4bpw-hb6-exl2 7 months ago

生成decode会有乱码

#1 opened 7 months ago by

New activity in TheBloke/Yi-34B-Chat-GPTQ 7 months ago

thank s for the model, I got some bad bytes when decoding Chinese

#2 opened 7 months ago by

KeyError: 'model.embed_tokens.weight'

#1 opened 7 months ago by

New activity in editing-images/leditsplusplus 7 months ago

Bad

#7 opened 7 months ago by

New activity in stabilityai/sdxl-turbo 7 months ago

When will a 1024x1024 turbo model will be out?

5

#8 opened 7 months ago by

New activity in berkeley-nest/Starling-LM-7B-alpha 7 months ago

Can use chatml format?

#15 opened 7 months ago by

New activity in latent-consistency/lcm-ssd-1b 7 months ago

Result not good

#4 opened 7 months ago by

New activity in 01-ai/Yi-34B-Chat-8bits 7 months ago

the int8 speed are very slow

#1 opened 7 months ago by