-
-
Trying to train with examples (trainer.yaml, unified_metric.yaml) I am facing some memory issues.
I changed "precision: 16-mixed" in trainer.yaml but it does not help. It starts ok with a low mem…
-
I tried to fine-tune XLM-Roberta Large model on Google Colab environment for 3 epochs using `1e-5` learning rate, 16 batch size, 2 accumulative steps and 120 warmup steps. But the loss didn't converge…
-
郑州智算项目 要把https://huggingface.co/maidalun1020/bce-embedding-base_v1 模型迁移到npu上 , bce-embedding-base_v1的介绍在https://github.com/netease-youdao/BCEmbedding/blob/master/README_zh.md
-
GPU:v100
cuda version: 12.2
Thanks for your great work. Now i wanted to deploy XLMRoberta with TensorRT-LLM, which is only has a tweak from the position_ids in bert_embeddings, so follow the issue…
ehuaa updated
6 months ago
-
マルチリンガルreranker
https://huggingface.co/corrius/cross-encoder-mmarco-mMiniLMv2-L12-H384-v1
Apache
-
I am trying to convert the deberta model to onnx for faster inference but got the following exception:
Exception: The current ONNX conversion only support 'BERT', 'RoBERTa', and 'XLMRoberta' mod…
-
I'm working on deploy huggingface roberta model to TensorRT-LLM, which has a little tweak from Bert with the embeddings.
In RobertaEmbedding the position_ids is calculated as follows:
![image](https…
ehuaa updated
10 months ago
-
**Description**
After deploying transformer model using triton inference server i am getting different output from the local copy of the same model.
**Triton Information**
23.03-py
Are you usi…
-
## Description
I'm trying to test [Vespa](https://docs.vespa.ai/) application with [custom Embedder](https://docs.vespa.ai/en/embedding.html) that uses DJL's HuggingFaceTokenizer under the hood.
…
dnmca updated
11 months ago