-
### Question
deepspeed --include localhost:1 --master_port 29597 llava/train/train_mem.py \
--deepspeed ./scripts/zero3.json \
--model_name_or_path /ssd1/suixin02/data/exp/llava/liuhaot…
-
I try
```bash
!python3 -W ignore llava/eval/run_llava.py \
--model-path Efficient-Large-Model/VILA-7B \
--conv-mode vicuna_v1 \
--query "\n Please describe the traffic condition." \…
-
Thank you for your excellent work. I encountered a problem when running multi-image input inference locally. After briefly looking at your code, I modified the inference command as follows:
`python -…
-
UPDATE (08/09/2023):
We have done major performance overhaul in the past few months, and now I'm happy to share the latest results:
- SOTA performance on CUDA: https://github.com/mlc-ai/llm-perf-b…
-
## 🐛 Bug
After building a custom ROCm TVM, compiling a model, and building a custom mlc-chat-cli, I end up with and assert error when trying to inference:
```
./build/mlc_chat_cli --local-id me…
-
`Train Epoch: [0] [ 2400/102750] eta: 5:20:57 lr: 0.000012 stage2-loss: nan stage2-cosine_loss: No data stage2-l2_loss: No data stage2-obj_norm: nan stage2-scene_norm: 0.0000 stage2-target…
-
Hello, I have been trying to use VideoChatGPT for single video inference/video demo and am having diffulties getting set up. I have followed the installation setup as laid out by the readme, and have …
rjccv updated
6 months ago
-
Trying to deploy and run demo on a 4 A6000 cluster but it seemed that the runtime froze without any exceptions... Could there be any possible problems? Sorry for asking a naive question and thanks for…
-
So I setup on 128GB RAM and 32 cores. I also used wizard vicuna for the llm model. I noticed that no matter the parameter size of the model, either 7b, 13b, 30b, etc, the prompt takes too long to gene…
-
M2 32g Mac Pro inference running extremely slow on llama 7b.
python generate.py --base_model=h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b
Same system benchmark running Llama.cpp:
vicuna-7b-1…