-
-
SUMMARY:
- [x] Avoid full pass through the model for quantization modifier
- [x] Data free `oneshot`
- [x] Runtime of GPTQ with large models – how to do a 70B model?
- [x] Runtime of GPTQ with act…
-
Hello.
**Error:**
```
=> Training epoch # 1
THCudaCheck FAIL file=/root/facedetect/torch/extra/cutorch/lib/THC/generic/THCStorage.cu line=65 error=2 : out of memory
/root/facedetect/torch/inst…
-
A bar chart renders data on a two axis plane, the X axis being some data type and the y axis being some value.
Considerations:
* Animate? Parallel or sequential?
* Data name?
* Y axis value…
-
`
class UserModel(tf.keras.Model):
def __init__(self,use_timestamps,use_distance):
super().__init__()
self._use_timestamps = use_timestamps
self._use_distance = use_distance
…
-
http://preview.d2l.ai.s3-website-us-west-2.amazonaws.com/d2l-en/master/chapter_deep-learning-computation/parameters.html
1.
mxnet:
```
print(net[0].collect_params())
print(net.collect_param…
-
**Description**
We have a Spark Application in Golden Zone (medallion arch.) that aggregates the input data, runs in batches in order to write out daily partitions. In the same spark application we…
-
## Is your feature request related to a problem? Please describe.
I'm looking to pass multiple feeds of sequential data from local instances to torchserve running on a remote instance. The cur…
-
**Describe the bug**
When deleting a (significant) number of messages while using the local index, they disappear momentarily and then reappear until the messages have been deleted on the server (?).…
-
Hello, thanks for this package!
I am trying to use your eANN to predict E/I connections in my data obtained from HD-MEA. I am following the notebook titled 'Use eANN'. If I understand correctly, th…