-
Asking this because you and i both know very well that even if it is possible to run big models with lower vram usage still it is not practical to use the models like that because your brain cells wil…
-
Hi!
First of all, thank you for your excellent work! I am currently trying to use pre-trained WavTokenizer models and I wanted to confirm the correct pairing between the available configuration fil…
-
nice work! I did some tests and found some codes in file "models/detector.py" could cause some problem:
```python
global_entity_list = [] # save all the entity type name for each senten…
-
Hey, as someone who now trained and evaluated both STEGO and SmooSeg, I think the original STEGO authors trained and evaluated Potsdam-3 on Vit-small, or am I crazy? Even their provided pre-trained mo…
-
Small Models are provided in https://github.com/ServerlessLLM/ServerlessLLM/blob/main/benchmarks/README.md, such as the test data of opt-6.7b. Compared with SafeTensors, sllm has a speed increase of a…
-
A user reported the following:
"A strange behavior of NetLogo with a MacBookPro M3 computer running Sonoma: both large and very small NetLogo applications suddenly become blocked, not responding eit…
-
### Problem to solve
LVGL have any plan to add 3D draw API ? Small 3D GPU (with the similar features of OpenGL ES 2.0) will be integrated to IoT devices soon.
### Success criteria
Support 3D draw A…
-
# Language Model Overview
## OpenAI
| | gpt-4o | gpt-4o-mini …
-
The EML211EditorView is currently difficult to maintain and extend due to its size and complexity. We need to make it more modular and readable in order to address issues users are encountering with s…
-
Let's implement chunking in the same way it was done in LLM2 to allow summarizing texts that are longer than the model context size.
* Implement chunking (maybe have the chunking logic in a service s…