PhilGlau
PhilGlau
Hi, just installed this a few minutes ago and ended up using the example code on the preliminary site (rather than the included code). Looks like the old activation methods...
``` def conv_layer(n_filters): return dp.Convolution( n_filters=32, filter_shape=(5, 5), border_mode='full', weights=dp.Parameter(dp.AutoFiller(gain=1.25), weight_decay=0.003), ) ``` shouldn't 'n_filters=n_filters' ?? Otherwise it seems like conv_layer is always fixed to 32 filters. UPDATE: looks like...
Missing an 'else' condition in fprop to handle passing 0.0 into dp.Dropout() to 'deactivate' a dropout layer. Obviously, one can just comment out a dropout layer in the network definition,...
On Arduinos [multiply is about 39x faster](https://forum.arduino.cc/index.php?topic=92684.0) than divide. Thus multiplying by 0.50 rather than dividing by 2.0 might make a difference on the get_micros() routine.
Sorry to post this in "Issues", but it doesn't appear that a "Discussions" option is available on this repository. It would be great if the project could handle speech that...
I'm crawling a large directory structure that contains 10s of thousands of high resolution images. Using the CNN() method, it OOMs before it finishes the scan. `Traceback (most recent call...
From flask_demo.py ``` response_json = { "text": str(response), "sources": [{"text": str(x.text), "similarity": round(x.score, 2), "doc_id": str(x.id_), "start": x.node_info['start'], "end": x.node_info['end'], } for x in response.source_nodes] } ``` When I run...
**Is your feature request related to a problem? Please describe.** I have ollama and openwebui running inside of a LXC privileged container **Describe the solution you'd like** Guidance on how...
### Feature Description It seems like right now only llm.chat() returns ThinkingBlocks. But that the 'thinking' portion of a response when using something like ```RouterQueryEngine()``` with tools that have thinking...