Skip to content

FreedomIntelligence/LongLLaVA

View on GitHub ↗Related repositories →

LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture

active 2024-09-052026-02-04 (UTC)

Partial coverage19,961 / 25,674 hourly files (78%) · 2 absent upstream · 5,710 failed, retryable2023-09-082026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
181
Pushes
20
Pull requests
1
Issues
20
Stars
124
Forks
5

Activity over time

Daily event counts in the loaded window

Line chart, 518 days from 2024-09-05 to 2026-02-04. Pushes: 20 total, peak 5 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 20 total, peak 5 in a day. Comments: 10 total, peak 3 in a day. Stars: 124 total, peak 16 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
wangxidong06382018
adelightday5002
maxin-cn2000
xuzukang1000
MXC66ai1000
zackschen1000
CuriousCat-71000
LongYu-LY1000
Jeremy-J-J1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#16wangxidong062025-08-25 02:46
    About the dataset and the construction
  • Issue#16zackschen2025-08-01 10:03
    About the dataset and the construction
  • Issue#14wangxidong062025-01-06 06:17
    CT frame numbers and frame resolution
  • Issue#12wangxidong062025-01-06 06:17
    additional auxiliary loss for moe?
  • Issue#13wangxidong062025-01-06 06:17
    LongLLava-Med
  • Issue#13LongYu-LY2024-10-29 07:17
    LongLLava-Med
  • Issue comment#11adelightday2024-10-16 01:59
    repository not found, token with permission
  • Issue#11adelightday2024-10-16 01:59
    repository not found, token with permission
  • Issue#11adelightday2024-10-14 05:19
    repository not found, token with permission
  • Issue comment#9wangxidong062024-10-12 02:54
    Can you provide the model path of longllava-9b?
  • Issue comment#8wangxidong062024-10-12 02:15
    device spec to run the inference
  • Issue#10wangxidong062024-10-12 02:15
    How to switch model from 13b to 9b
  • Issue#7wangxidong062024-10-12 02:15
    the role of moe
  • Issue#4wangxidong062024-10-12 02:14
    There are many bugs when pip the requirement.txt as follows, making the code hard to run, can you provide more details?
  • Issue#5wangxidong062024-10-12 02:14
    ImportError: cannot import name 'LlavaPhiForCausalLM' from 'llava.model'
  • Issue#3wangxidong062024-10-12 02:14
    Missing supporting init.sh and VisionJamba found when running MultiImageSFT.sh
  • Issue comment#10wangxidong062024-10-12 02:13
    How to switch model from 13b to 9b
  • Issue#9xuzukang2024-10-09 06:22
    Can you provide the model path of longllava-9b?
  • Issue comment#8adelightday2024-10-07 03:42
    device spec to run the inference
  • Issue#8adelightday2024-10-05 11:36
    device spec for inference
  • Issue#7maxin-cn2024-10-01 04:03
    the role of moe
  • Issue#6maxin-cn2024-10-01 03:59
    Architecture of LongLLaVA
  • Issue comment#6wangxidong062024-09-30 01:42
    Architecture of LongLLaVA
  • Issue comment#5wangxidong062024-09-29 04:03
    ImportError: cannot import name 'LlavaPhiForCausalLM' from 'llava.model'
  • Issue#5Jeremy-J-J2024-09-29 03:30
    ImportError: cannot import name 'LlavaPhiForCausalLM' from 'llava.model'

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 124 stars here means stars gained during the window, not the repo's star count.