-
### Description
When reviewing the Messages list, we discovered issues with the right-aligned date stamp that appears on the Message list item. When larger font sizes are enabled or the app is rendere…
-
```
The configure line used in current ubuntu and debian packages of ffmpeg-damnvid
makes the binary unredistributable:
./configure --enable-memalign-hack --enable-libxvid --enable-libx264
--enable…
-
Quick question, does Auto Train support fine tuning models like Donut for VQA or classification?
-
Hi!
Thanks for your excellent work!
As far as I know, Internvideo calculates similarity between video feature and text feature, and it need an action label set to do this classification task.
But i…
-
Hello! Thank you for your outstanding work.
I tried to reproduce the code that evaluates the `Quilt_VQA`, but I find that there are 2 versions of the code. The first is `quilt-llava\scripts\v1_5\e…
lsnls updated
5 months ago
-
Recently, I try to reproduct the metric result of TextVQA datasets.
When I run the evaluation code in TextVQA, and I got the `TextVQA_test_pred_official_eval.json`. According the instruction, I subm…
SWHL updated
4 months ago
-
再请教一个问题,训练好的sat模型如何再两张GPU上加载并推理? 我目前只有A100(40G)的版本,有时推理会报内u才能溢出。
请问如何设置多GPU推理?
下面模型加载部分如何设置呢?谢谢
`# load model
model, model_args = AutoModel.from_pretrained(
args.from_pretra…
-
# Updated Summary and QA Instructions April 2023:
Videos are still not playing because there is an error in the manifest. Make sure they can display correctly
# Acceptance Criteria April 2023:
- [ ] …
-
下面是我的训练脚本:
```
NODE_RANK=0 \
MASTER_ADDR=localhost \
MASTER_PORT=7777 \
NPROC_PER_NODE=8 \
swift sft \
--model_type internlm-xcomposer2-7b-chat \
--model_id_or_path /data/rotate_712 \
…
bonre updated
1 month ago
-
Command:
python scripts/merge_lora_weights.py --model-path /home/rohith/Documents/mistral-llava/ --model-base /media/rohith/CC2A79902A7977F2/models/llava-v1.6-mistral-7b/ --save-model-path /hom…