Skip to content

Pull requests: haotian-liu/LLaVA

New pull request New
42 Open 114 Closed
42 Open 114 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Anyres compatible fine-tuning of llava-1.6 mistral 7b and 34b
#1347 opened Mar 27, 2024 by arielnlee Loading…
16
Added 'sys.append' with EAFP for Colab fine-tuning
#1325 opened Mar 23, 2024 by TongmengXie Loading…
2
Fix loading pretrained-mm-projector errors under Deepspeed Zero3.
#1250 opened Mar 8, 2024 by lockon-n Loading…
[Feature] Adding support for Mixtral and Gemma models
#1247 opened Mar 8, 2024 by martinakaduc Loading…
4
enabling mistral training by adding mistral template
#1211 opened Mar 1, 2024 by Jayantverma2 Loading…
2 tasks done
2
Changes to image handling, added arguments and eval_model function.
#1205 opened Feb 29, 2024 by verzic Loading…
1
Builder torch_dtype FIX
#1181 opened Feb 26, 2024 by mosheber Loading…
Refactor run_llava to avoid duplicated model loading if multiple evaluation is required
#1160 opened Feb 21, 2024 by yeyimilk Loading…
remove duplicate PIL
#1159 opened Feb 21, 2024 by AndrewTrefilov Loading…
add Qwen1.5 in LLaVA
#1146 opened Feb 18, 2024 by yiyexy Loading…
11
Add instructions on running llava-v1.6-mistral-7b
#1115 opened Feb 10, 2024 by aliencaocao Loading…
3
9
Fix a bug in function "prepare_inputs_labels_for_multimodal" of "LlavaMetaForCausalLM" when there are more than one image in each conversation of a batch.
#967 opened Jan 3, 2024 by zsxm1998 Loading…
Timmvit and laion data
#966 opened Jan 3, 2024 by yudongliu97 Loading…
@haotian-liu
Made gradio an optional dependency
#809 opened Nov 15, 2023 by nb-programmer Loading…
Update README.md, minor typo correction
#798 opened Nov 14, 2023 by vishnumadhu365 Loading…
reduce cyclomatic complexity
#574 opened Oct 14, 2023 by tonyaklm Loading…
1
feat: use torch2 implemented flash attn
#215 opened Jun 4, 2023 by wade3han Loading…
2
ProTip! Follow long discussions with comments:>50.