-
**Describe the issue**
This is actually not a issue but a simple question which is I have run bfcl generate on llama3.1 with python_ast test category and I got list of results from model. Next, If I …
-
Hi,
To version each project separately in nx, I'm using Independent Mode. However, I'd like to generate a Changelog for all of the projects in the root, rather than on a project-by-project basis.
I…
-
Hello,
I am still playing around with the awesome code you produced and I really like the way you implemented GG20 in the other dev branch using `round-based` etc. While working with the code there…
-
Hello @patil-suraj,
I get the following assertion error:
Code:
```
gen = pipeline("question-generation", model='valhalla/t5-base-qg-hl', ans_model='valhalla/t5-base-qa-qg-hl')
qa = gen('Dire…
-
Because of C# compiler still does not allow to generate expressions from statement lambdas (CS0834), is it feasible to have some workaround in the Salterelle Compiler? For instance my first idea:
An …
-
I am attempting to generate new TagStandard41h* and TagStandard52h* families and I am seeing extremely long generation time estimates. I have attempted to generate some of the larger Standard families…
-
I'm trying to implement various methods from the [patchscopes](https://arxiv.org/abs/2401.06102) paper, and some of them utilize token generation to eg. explain the meaning of a patched representation…
-
### Your current environment
```text
Your output of `python collect_env.py` here
```
### Model Input Dumps
_No response_
### 🐛 Describe the bug
When I load LLM as:
`llm = LLM(
…
-
### 🚀 The feature, motivation and pitch
temperature/top_k/top_p These values will affect the model output,The default value should be read from generation_config.json if the user does not set it.
…
-
### Checklist
- [ ] 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.…