-
gimme ur dc
8FrMc updated
2 months ago
-
Trying to run following gpt2 demo with triton-cpu and certain tirton kernel fails with above error:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from torch._…
-
### Describe your problem
refer [code](https://github.com/infiniflow/ragflow/blob/v0.12.0/api/db/services/dialog_service.py#L194).
```python
if not llm:
llm = TenantLLMService.query(te…
-
Currently the JWTAuth security scheme assumes the token from the HTTP header only
With the latest release of adding cookie in the design, the The JWTAuth security scheme should be able to read the …
-
Hi team,
I would like to request some support for adding additional features for T5Tokenizer / SentencepieceTokenizer. I was able to convert the HuggingFace T5 Tokenizer to Onnx format using the follo…
-
Hi and thanks for this great library!
Iam very new to onnx and Iam trying to include the Roberta tokenizer into a Roberta onnx model.
As far as I have understood, one can get the onnx graph for th…
-
### Describe the issue
I'm trying to load a model I've converted from gguf to onnx using `optimum-cli` and I get this error (Can't create a session).
### To reproduce
I'm following the example http…
-
I am experiencing a memory leak while running my application, which is to run an MMLU accuracy test on my Radeon 780M iGPU via DirectML.
Each inference adds tens-hundreds of megabytes to the total …
-
the command:
`python3 -m accelerate.commands.launch --config_file=accelerate_multi_GPU.yaml --num_processes=4 -m lmms_eval --model llava_hf --model_args pretrained="llava-hf/llava-1.5-7b-hf" --tasks …
-