Spaces:

llamafactory
/

PaliGemma-3B-Chat-v0.2

Running on Zero

Great work!

by merve HF staff - opened Jun 3

Jun 3

Hello @hiyouga great work! This model wasn't finetune-able with multiple conversation turns, how were you able to overcome this? Also would be great to add example inputs :)

hiyouga

LLaMA Factory org Jun 3

Hi @merve ! we provided our training recipes at https://huggingface.co/hiyouga/PaliGemma-3B-Chat-v0.1#training-procedure

merve

Jun 3

@hiyouga Hello again! wanted to ask whether you provided conversation turns or not, which is not given there from what I saw

hiyouga

LLaMA Factory org Jun 3

Please refer to this dataset: https://huggingface.co/datasets/BUAADreamer/llava-en-zh-2k?row=0

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment