-
### Describe the bug
`Ctrl+N` and `Down` should have identical behavior in Emacs mode, but `Ctrl+N` seems to invoke the completion menu, while `Down` simply moves down the command history (as expecte…
-
gulp-polylint seems to fail in Gulp 4 using the most paired-back code possible:
```
function markup() {
return gulp.src(sourceFiles)
.pipe(polylint());
}
```
> Starting 'markup'...
> The follo…
-
用以下方式验证glm4-9b-chat模型的输出，serving端报错
curl --request POST \
--url http://127.0.0.1:8000/v1/chat/completions \
--header 'content-type: application/json' \
--data '{
"model": "glm-4-9…
-
Hey @PavelLaptev, I just tried the plugin and it works like a charm ✨
Would you be interested on an intial PR to support [edit](https://platform.openai.com/docs/api-reference/edits) & [chat](https:…
-
The farming timers are a great addition but with so many patches and types it can be a little bit of a nuisance to find the information I'm interested in. The completion of farming contracts can influ…
-
### by using DynamicCache llm don't need to re compute the previous prompt. it can re use previous prompt kv cache!
### In gemini it's called context caching gemini & in anthropic it's called prompt …
-
### Please confirm you have already done the following
- [X] I have searched the repository for related/existing bug reports
- [X] I have all the details the issue requires
### Please answer the fol…
-
The project looks interesting. I was looking for information of what the trained model can do. Video, screenshots, or even just a few sample prompt / completion pairs for, say, the Wikipedia trained v…
-
After last update I got strange behavior of neosnippet: it doesn't complete expression but inserts **<Plug>(neosnippet_expand)** instead.
I have replaced "neocomplcache" group with "neocomplete…
-
need to benchmark my quantization against the OG model to see variance, determine how much accuracy we sacrifice and how much speed we gain.