-
does not use docker-compose.
step1.Start the ray_head node
```
docker run -d \
--name ray_head \
--privileged \
--env MODEL_FOLDER=${MODEL_FOLDER} \
--env RAY_NUM_CPUS=8 \
-p 6379:…
-
I run lightrag_hf_demo.py, but there is no response after running it. Does anyone know what is going on?
My code is as follows:
```
import os
from lightrag import LightRAG, QueryParam
from …
-
**Describe the bug**
When using Flash Attention (--use-flash-attention true) to train Qwen2VL model with mixed data (both image and text data), the code will yield the following error
```
[rank0]: …
-
1.PARE: Part Attention Regressor for 3D Human Body Estimation(2021)
img-->volumetric features(before the global average pooling)-->part branch: estimates attention weights +feature branch: performs S…
-
### Feature request
Currently, if fp16 is used with grounding dino via https://huggingface.co/docs/transformers/main/en/model_doc/grounding-dino, there is an error of the following:
```
...
Fi…
-
This is a "living issue". Editing is appreciated.
### Context:
- Most prominent benchmark for embedding models: https://huggingface.co/spaces/mteb/leaderboard
- We can choose to index the pdf dat…
-
## 🐛 Bug
When training models: 'vicuna-7b-v1.5-16k', 'longchat-13b-16k', 'Mistral-7B-v0.2', 'falcon-180B', 'Llama-3-70B', 'CodeLlama-34b-hf' with FSDP and FP8 we get KeyError: 'scaling_fwd'. This m…
-
**Describe the bug**
I am running data preprocessing script using the following command:
```
python tools/preprocess_data.py \
--input ./openwebtext/scraped_100/train_data.json \
--…
-
Great work!
I am trying to run pyramidinfer with a Llama3-8B-Instruct model, but it seems that the version of "transformers" is too old to load the weight of Llama3-8B model.
I ran this command …
-
### System Info
- `transformers` version: 4.46.2
- Platform: Linux-5.15.0-120-generic-x86_64-with-glibc2.35
- Python version: 3.10.15
- Huggingface_hub version: 0.26.2
- Safetensors version: 0.…