-
### Description
Currently the project requires the language model name after `-m`. Although `-g` option can be used to view all available models, it is an extra step.
This issue proposes that the …
-
hi, for the txt image genreateion, why not try using existed LLMs, plus the decoder in tokenizer, and training the whole model with lora?
just like SEEd does.
So that it at least won't harm the …
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [x] 2. The bug has not been fixed in the latest version.
### Describe the bug
RuntimeError: CUDA error: dev…
ZGW99 updated
4 months ago
-
Thanks for sharing this interesting work.
I was wondering how do you do the inference on text-only tasks such as MMLU? Do you just use Llama3?
If so, this work actually keeps two models, one is Llam…
viyjy updated
2 months ago
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
- [X] 3. Please note that if the bug-related issue y…
-
Hi, Thanks for the great work.
I have finetuned the model using [LLaVA-More](https://github.com/aimagelab/LLaVA-MORE) repository on llama3. Now when I try to adapt your code I am getting `Attribute…
-
The [Mixture of Agents (MoA)](https://arxiv.org/abs/2406.04692) is an innovative approach to leveraging the collective strengths of multiple language models to enhance overall performance and capabili…
-
There are two existing (closed) issues related to this, but neither offers a solution. I've tweaked the n_ctx value, but the error persists: 2048 tokens aren't enough. So, is this parameter ineffectiv…
-
I attempted a workaround, but the output from finetuning doesn't look quite right. Has anyone made a working fix for this issue?
-
I am trying to reproduce the MMVP benchmark performance of Eagle-X4-8B-Plus.
Could you provide the official code or scripts for this, as I am unable to match the published benchmarks?