-
### What is the issue?
When using different context sizes (`num_ctx`) with the Ollama embedding model, I noticed big differences in the cosine similarity of the embeddings. Specifically, when I set t…
-
### Issue
Sharing some thoughts on how to make Aider benchmark closer to real development and detecting potential overfitting issues. During the trials, the aider agent should not have access to th…
-
-
- [ ] [huh/README.md at main · charmbracelet/huh](https://github.com/charmbracelet/huh/blob/main/README.md?plain=1)
# Huh?
A simple, powerful library for building interactive forms…
-
### Current Behavior
Using the default onnx model,
**Score function**
```
def get_score(a, b):
return evaluation.evaluation(
{
'question': a
},
{
…
-
I am planning to refactor the [existing Embeddings class](https://github.com/holoviz/lumen/blob/main/lumen/ai/embeddings.py#L6).
The purpose is to supply LLMs with up-to-date or private data using re…
-
When viewing the diff of a commit from the graph, or when viewing the full diff of changes or staged changes, "moved or renamed" files are not shown as such, but they are shown as separate delete and …
-
## Description
The web UI allows users to see the matching item pairs above a given threshold
Can we make the R library also return the matching pairs above a threshold? This is called the cross…
-
Hi, thank you for your wonderful work! I notice that in the training process, the loss function is composed of the attention loss and the cam_up_similarity. Since the cam_up_similarity was not discuss…
-
Recently I am reproducing your code, can you provide the source code for the implementation of Figure 3?