Peter Devine comments

Results 8 comments of


                                            Peter Devine

Cannot deploy Huggingface model onto serverless endpoint

But if I want to make a serverless endpoint (as described here - https://aws.amazon.com/about-aws/whats-new/2021/12/amazon-sagemaker-serverless-inference/), then I cannot supply an instance type, as this option explicitly has no defined instance. In...

[FEATURE] Merge Peft Adapter to base model

Bump. I'd love this feature so that I can run vLLM with my quantized model. Thanks.

Support loras on quantized models

@fmmoret Any way I can help? This would be an awesome feature so I'd hate to see its inclusion falter.

Azure OpenAI Embedding langchain.embeddings.openai.embed_with_retry won't provide any embeddings after retries.

Wrong results with Faceboxesv2 (ONNX) and there isn't YoloV5face implemented yet.

Bump

Successful pip Installation Results in ModuleNotFoundError

Evaluate on specified data

Bump. It would be really handy to be able to evaluate continuously on a specified dataset different from the training dataset so that we could control early stopping etc. based...

[Bug] Test set is taken from training set

PS, being able to change the ratio (or number of examples) of the test set [when it is automatically generated](https://github.com/artidoro/qlora/blob/7f4e95a68dc076bea9b3a413d2b512eca6d004e5/qlora.py#L547) (i.e., making it so that instead of a setting test_size...