-
It is possible to convert GPTQ models without act_order (when g_idx is not used) to AWQ gemv compatible format since AWQ gemv changed the pack order to a natural order.
GPTQ storage format:
```
q…
-
Our ONNX converters could be improved.
To convert from pytorch [ONNX dynamo](https://pytorch.org/docs/stable/onnx_dynamo.html) looks promising.
-
Hi,
Downloading llama models from hugging face requires llama to previously authorise your account. it's two weeks since I submitted the request, but it is still pending. So, I downloaded the mode…
-
For enhancing accessibility and collaboration, we can upload the CAM model and its weights to the Hugging Face Hub. This requires converting the model weights into PyTorch's `.pt` format to ensure com…
-
After converting keras model to caffe model, the weights in each layer became zero. What is the possible reason for this? thanks
-
## ❓ Question
im able to `torch.export` and generate an ExportedProgram with no issues for my model. upon compiling with `torch_tensorrt`...
```python
ep = torch.export.load("...")
example_inpu…
-
Hello,
We converted the paxml checkpoint and resumed training with following config:
```
base_config: "base.yml"
tokenizer_path: "/dockerx/vocab/c4_en_301_5Mexp2_spm.model"
dataset_type: "tfds"
…
-
Hey!
In the TFJS API, there is a `getWeights()` fcn that returns a tensor containing the weights of the model. I tried converting this tensor into a json and send that to a python server containing…
-
**Is your feature request related to a problem? Please describe.**
Currently, if `torch_dtype` is not specified, the pipeline defaults to loading in `float32`. This behavior causes `float16` or `bflo…
-
Hello, dear developer.
I used jetson xavier nx, ubuntu 18.04, cuda 10.2, tensorRT 8.0.1.6, jetpack 4.6, to compile the model, and I found the following error, which caused the model conversion to fai…
avdvg updated
3 weeks ago