Alessandro Giagnorio

DPO models generate multiple / corrupted responses

57

Hi, I am running some tests with DPOTrainer to see how it works but I have encountered some problems during the inference phase of the generated model. In details, this...

Hello, do you know up to what date ( approximately ) the data for model training was collected?

Information about the position of the modified lines / tokens

5

Hi, thank you very much for implementing this library. I would like to have more information about its use for the following scenario: given two code snippets, I would like...

Replicating KBLaM on different knowledge bases

3

Hello, Thank you for sharing KBLaM's source code. I'd like to know more about the reproducibility of this work on different knowledge bases. According to what I've read, these are...

Error during evaluation with multiple completions

1

Hello! Thanks for your effort in releasing ClassEval benchmark. I am evaluating some models on your benchmark, but I am experiencing a problem when I run the evaluate.py script. In...

[Feature] Improve clarity about LLM configs in the documentation

7

### What feature would you like to see? Currently, it is possible to setup configurations such as the temperature of the LLM both via ``dspy.LM(...)`` ([documentation link](https://dspy.ai/learn/programming/language_models/)) and ``dspy.Predict()`` (and...