Benhao Huang

Reproduced the middle plot of fig2 in the paper, using a logistic regression model trained on MINIST 10-class as described in the paper. For convenience, I have include all the...

try codium

4

@CodiumAI-Agent /review

## Description I have implemented a GLI bot capable of answering questions based on GLI docs using Langchain. When an issue comes or a new comment made in PR/issue section,...

**Describe the bug** When I tried to add some str type date into Node Attributes, I found that Attribute class fails to automatically detect the data format of the data....

https://github.com/eric-mitchell/direct-preference-optimization/blob/f8b8c0f49dc92a430bae41585f9d467d3618fe2f/trainers.py#L297C1-L302C1 ``` if self.config.sample_during_eval: all_policy_samples, all_reference_samples = [], [] policy_text_table = wandb.Table(columns=["step", "prompt", "sample"]) if self.config.loss.name in {'dpo', 'ipo'}: reference_text_table = wandb.Table(columns=["step", "prompt", "sample"]) ``` Just make sure it's not...

Bad performance on PrOntoQA benchmark

1

**PrOntoQA** is a question-answering dataset that generates examples with chains-of-thought that describe the reasoning required to answer the questions correctly. The sentences in the examples are syntactically simple and amenable...

fixed ERROR: No matching distribution found for absl

1

`absl` -> `absl-py`


Anyone tried using LCM-LoRA to accelerate inference of CogVideoX?

1

We greatly appreciate the generation quality of CogVideoX; however, its generation speed remains a notable limitation. I am currently working on using the Latent Consistency Model (LCM) to accelerate the...