-
Are there any plans or interest in integrating a word/phrase aligner?
I'm not aware of any javascript based libraries that are available to integrate. I do have a background in creating and modifying…
-
When using tfp.layers.Convolution1DFlipout and tfp.layers.DenseFlipout in the same model calling apply_gradients() (using custom training loop and GradientTape()) raise error: TypeError: Can not conve…
aikho updated
4 years ago
-
你好，请问一下就是怎么将weights.zip里面对应的模型文件转换成onnx格式的模型文件。
我这边转换时，使用的是transformers 官方提供的脚本[convert_graph_to_onnx.py](https://github.com/huggingface/transformers/blob/main/src/transformers/convert_graph_to_onn…
Bycqg updated
4 months ago
-
Hi Team,
When I am loading the Mixtral-based SFT MoE model 'DAMO-NLP-SG/VideoLLaMA2-8x7B' using the same inference code provided in the README.md, the following error is raised:
```
Traceback (…
-
## Introduction
I am writing to request a feature implementation for Haystack in Node.js. As a developer working extensively with JavaScript and Node.js environments, I find Haystack's capabilities…
-
Sample datasets randomly selected are available. Currently, there is no unified testing framework to ensure that outputs from cleaning, NLP processing/vectorization, and future work meets database mo…
-
```
2018-03-10 01:13:05.554114: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
…
-
Hi! in the recipe, if i do not want to quantize and perform structured pruning, is it okk to give quantize:false like below and do not provide QuantizationModifier in the recipe?
SparseGPTModif…
-
Hi HF Team
Thanks a lot for this repo.
I was exploring the code and trying to run it with the example provided in Readme file.
But it throws this error related to protobuf.
Here is the error:
`20…
-
I ran the following code on colab:
```python
from pipelines import pipeline
nlp = pipeline("question-generation")
text = """FIO Labs is an independent, privately-owned company with a global re…