-
Great repo! Here are some complementary related works on Multimodal LLM
- POPE: Polling-based Object Probing Evaluation for Object Hallucination (2023.05.17)
- https://github.com/RUCAIBox/POPE
…
-
Hi, nice work on Multimodal LLM. Would you mind adding [mPLUG-Owl](https://github.com/X-PLUG/mPLUG-Owl/) into your evaluation so we can better known it's power.
Thanks.
-
### Describe the bug
Can run build-in llava-13b multimodel on web UI. However, when hitting the API, got VRAM OOM issue.
Even tried to reduce the max gpu memory from 10 to 6, still got the same OOM …
-
I was going through the small example on the [homepage of the docs](https://docs.jina.ai/), and it gives me a weird error:
```console
WARNI… gateway@6246 Getting endpoints failed: failed to connec…
-
Greetings! I noticed that your README has a demo image of Visual Instruction model, but I wasn't able to find relevant code for it. Is it already supported in v2 or is it planned for v3? Will it work …
-
## Date
Monday, August 14, 2023 - 9:30am ET / 2:30pm UK
_// Second Monday of every month_
## Attendees
| Fullname | Affiliation | GitHub Username |
|:-----|:-----|:-----|
| James McLeod …
-
When running a tweaked version of the sample code it looks the AgentExecutor chain loop stucked, repeating itself ( in Action and Action Input ):
```
Entering new AgentExecutor chain...
Thought: Do…
-
Hi! I attempt to implement the multi-modal ability of llama-adapter-v2 myself and I've already done most of the code using `transformers` and `peft`. But there are some details I'm not so sure, and if…
-
Could you point me to where in your provided code the multimodal adapter is implemented?
-
Hi! I just went through your preprint, and here are my two quick reactions, if you don't mind:
### Typo in the Figure 3 caption of the preprint
> (b) “Unssen tokens” are data units that have not y…