-
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 …
-
### 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(
…
-
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…
-
### 🚀 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.
…
-
I have a question regarding the generation of style_motion files.
I would like to test using a different style_motion than the one provided. While I noticed the BaseModel.save_npy() function in you…
-
Both the evaluation and testset generation are computationally and monetarily expensive.
It is very painful to experience a crash after several expensive hours of evaluation or generation, only to …
-
Develop a backend feature that allows users to generate a quiz from a selected textbook chapter. The backend should send the content of the chapter to an LLM and request it to create a quiz. The resul…