Raushan Turganbay

#2 opened 2 days ago by

RachelZhou

New activity in llava-hf/llava-v1.6-34b-hf 3 days ago

How do you fine tune LLaVA NeXT?

26

#5 opened 6 months ago by

Nishgop

New activity in llava-hf/llava-1.5-7b-hf 5 days ago

populate "text_config"

#34 opened 5 days ago by

ngxson

New activity in llava-hf/llava-v1.6-mistral-7b-hf 8 days ago

Index out of range errors

#32 opened 15 days ago by

manas03

TypeError: LlavaNextProcessor.init() got an unexpected keyword argument 'image_token'

#22 opened 4 months ago by

BenjaminTT

Why does the "llava-hf / llava-v1.6-mistral-7b-hf " not support system role?

#31 opened 17 days ago by

Yujie-AI

New activity in llava-hf/llama3-llava-next-8b-hf 8 days ago

fine tuning

#3 opened 12 days ago by

michelgi

New activity in llava-hf/llava-onevision-qwen2-7b-ov-hf 18 days ago

add "mm_spatial_pool_mode" to config.

9

#3 opened 24 days ago by

litianjian

New activity in llava-hf/llava-1.5-7b-hf 20 days ago

I encountered an error while running the official example

3

#33 opened 20 days ago by

jackyjin

New activity in lmms-lab/llava-onevision-qwen2-72b-ov-chat 21 days ago

correct pipeline tag

#3 opened 21 days ago by

New activity in lmms-lab/llava-onevision-qwen2-7b-ov-chat 21 days ago

correct pipeline tag

#2 opened 21 days ago by

New activity in llava-hf/LLaVA-NeXT-Video-7B-hf 24 days ago

Best practice for fine-tuning llava-next-video-7b

7

#2 opened 3 months ago by

study-hjt

New activity in llava-hf/llava-onevision-qwen2-0.5b-ov-hf 24 days ago

Error when attempting to run either model... ValueError: embed_dim must be divisible by num_heads (got `embed_dim`: 1152 and `num_heads`: 14).

#4 opened 24 days ago by

jdc4429

New activity in llava-hf/llava-onevision-qwen2-72b-ov-hf 27 days ago

Bug in 4bit quantization?

#1 opened 29 days ago by

prasb

New activity in llava-hf/llava-v1.6-vicuna-7b-hf 28 days ago

Is there any code for fine-tuning the LLAVA model?

#6 opened about 2 months ago by

miaoyl

New activity in llava-hf/llava-interleave-qwen-7b-hf 30 days ago

pass multi-images to the processor

3

#2 opened 3 months ago by

Benjamin02

New activity in llava-hf/llava-v1.6-mistral-7b-hf about 1 month ago

Llava on llama.cpp?

#30 opened about 1 month ago by

danielelongo

Model stuck until max_new_tokens?

#29 opened about 1 month ago by

danielelongo

PLZ!😭When I run the template, I get the error“Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained."

5

#26 opened 3 months ago by

wenyilll

New activity in lmms-lab/llava-onevision-qwen2-7b-ov about 1 month ago

Are Quants possible?

#9 opened about 1 month ago by deleted

New activity in Qwen/Qwen2-VL-7B-Instruct about 1 month ago

add correct pipeline tag

#4 opened about 1 month ago by

New activity in llava-hf/README about 1 month ago

config conversion from llava repo

#2 opened about 1 month ago by

mjbooo

New activity in KangarooGroup/kangaroo about 1 month ago

Change pipeline tag

#3 opened about 1 month ago by

New activity in llava-hf/llava-1.5-7b-hf about 1 month ago

convert llava-v1.5-7b to liuhaotian/llava-v1.5-7b-hf format

21

#26 opened 5 months ago by deleted

New activity in Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8 about 1 month ago

add correct pipeline tag

#1 opened about 1 month ago by

New activity in Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4 about 1 month ago

add correct pipeline tag

#2 opened about 1 month ago by

New activity in Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4 about 1 month ago

add correct pipeline tag

#1 opened about 1 month ago by

New activity in Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8 about 1 month ago

add correct pipeline tag

#1 opened about 1 month ago by

New activity in Qwen/Qwen2-VL-7B-Instruct-AWQ about 1 month ago

add correct pipeline tag

#1 opened about 1 month ago by

New activity in Qwen/Qwen2-VL-2B-Instruct-AWQ about 1 month ago

add correct pipeline tag

#1 opened about 1 month ago by

New activity in Qwen/Qwen2-VL-2B-Instruct about 1 month ago

add correct pipeline tag

#2 opened about 1 month ago by

New activity in llava-hf/llava-v1.6-mistral-7b-hf about 1 month ago

Support for multiple images..

8

#19 opened 5 months ago by

wamozart

New activity in llava-hf/llava-v1.6-vicuna-13b-hf about 1 month ago

AttributeError: 'LlavaNextProcessor' object has no attribute 'apply_chat_template'

6

#6 opened about 1 month ago by

67L1

New activity in llava-hf/llava-1.5-13b-hf about 1 month ago

How to convert new LLaVA model into HF format?

7

#9 opened 5 months ago by

zzxslp

New activity in llava-hf/llava-interleave-qwen-0.5b-hf about 1 month ago

How to Run ONNX Model

#7 opened about 2 months ago by

ha1772007

How to export ONNX from finetune llaval-interleave model

5

#8 opened about 2 months ago by

jasonwang110

New activity in facebook/chameleon-7b about 1 month ago

Chat template available?

3

#8 opened 2 months ago by

mmordig

New activity in llava-hf/llava-onevision-qwen2-0.5b-ov-hf about 2 months ago

lm head weights missing?

#3 opened about 2 months ago by

mdoeir

New activity in llava-hf/llava-onevision-qwen2-0.5b-si-hf about 2 months ago

The question about the using of onnx model?

#3 opened about 2 months ago by

jasonwang110

Upload ONNX weights

#2 opened about 2 months ago by

Xenova

New activity in llava-hf/llava-onevision-qwen2-0.5b-ov-hf about 2 months ago

Upload ONNX weights

#2 opened about 2 months ago by

Xenova

New activity in llava-hf/llava-onevision-qwen2-0.5b-si-hf about 2 months ago

Fix typos

#1 opened about 2 months ago by

Xenova

New activity in llava-hf/LLaVA-NeXT-Video-7B-hf about 2 months ago

Fix model_type to llava_next_video

#4 opened about 2 months ago by

tkoniy

New activity in llava-hf/llava-onevision-qwen2-0.5b-ov-hf about 2 months ago

Download transformers for LlavaOnevisionForConditionalGeneration

#1 opened about 2 months ago by

mjbooo

New activity in llava-hf/llava-onevision-qwen2-7b-ov-hf about 2 months ago

Can I use multi-image input?

#2 opened about 2 months ago by

juhonov

New activity in llava-hf/llava-onevision-qwen2-72b-si-hf about 2 months ago

Can You please Make Llava 1.6 qwen2 0.5B

#1 opened about 2 months ago by

ha1772007

New activity in llava-hf/llava-onevision-qwen2-7b-ov-hf about 2 months ago

Some error with this model

#1 opened about 2 months ago by

lsx666

New activity in llava-hf/LLaVA-NeXT-Video-34B-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#2 opened about 2 months ago by

Update chat_template.json to incorporate `generation` tag

#1 opened about 2 months ago by

New activity in llava-hf/LLaVA-NeXT-Video-7B-32K-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#1 opened about 2 months ago by

New activity in llava-hf/LLaVA-NeXT-Video-7B-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#3 opened about 2 months ago by

New activity in llava-hf/llava-1.5-13b-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#13 opened about 2 months ago by

New activity in llava-hf/llava-1.5-7b-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#29 opened about 2 months ago by

New activity in llava-hf/llava-v1.6-vicuna-13b-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#5 opened about 2 months ago by

New activity in llava-hf/llava-interleave-qwen-0.5b-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#6 opened about 2 months ago by

New activity in llava-hf/llava-interleave-qwen-7b-hf about 2 months ago

Update chat_template.json to incorporate `generation` tag

#6 opened about 2 months ago by

New activity in llava-hf/README about 2 months ago

Next generation of Llava models

#1 opened 2 months ago by

nassimab

New activity in llava-hf/llava-v1.6-mistral-7b-hf 2 months ago

Several issues loading and using the model with transformers==4.39.2

#7 opened 6 months ago by

csegalin

New activity in llava-hf/llava-v1.6-vicuna-7b-hf 2 months ago

Update chat_template.json to incorporate `generation` tag

#5 opened 2 months ago by

New activity in llava-hf/llava-v1.6-34b-hf 2 months ago

why the output only contains "\n"???