Shreyas Subramanian

Trying to convert Optimal ad problem to DPP

1

When I try the following example and check for dpp True: ``` # Generate data for optimal advertising problem. import numpy as np np.random.seed(1) m = 5 n = 24...

How to load + predict using pretrained models

2

Hi, Thanks for sharing your great work! I am trying to use your pretrained models for prediction with the test airfoils. What I have tried so far is to load...

MindSmallReranking dataset errors out due to download/parsing error?

5

Tested with the latest mteb on pypi from 4 hours ago as well as installation from latest git main branch: ``` ## Evaluating 1 tasks: ───────────────────────────────────────────────── Selected tasks ───────────────────────────────────────────────── Reranking...

Merging fails with RuntimeError: weight required but not present in model

7

I'm trying to merge some embedding models with this config file. the architectures are similar but I think it is erroring out on some names of layers? Would love some...

pip install fails with package error

2

``` /opt/conda/lib/python3.7/site-packages/secretstorage/dhcrypto.py:16: CryptographyDeprecationWarning: int_from_bytes is deprecated, use int.from_bytes instead from cryptography.utils import int_from_bytes /opt/conda/lib/python3.7/site-packages/secretstorage/util.py:25: CryptographyDeprecationWarning: int_from_bytes is deprecated, use int.from_bytes instead from cryptography.utils import int_from_bytes Collecting sagemaker-studio-image-build Using cached sagemaker_studio_image_build-0.6.0.tar.gz...

*Issue #, if available:* *Description of changes:* By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

Added Langchain to BR migration example

1

*Issue #, if available:* N/A *Description of changes:* Added an example to migrate from langchain to BR By submitting this pull request, I confirm that you can use, modify, copy,...

Model not supported - needed for research paper - b1ade-1b-bf16

1

Hi, Not sure what is needed to support a model yet, and happy to help if I can. Here is the error: ``` NotImplementedError: Unsloth: w601sxs/b1ade-1b-bf16 not supported yet! Maybe...

Unsloth GRPO trainer error - IndexError: argmax(): Expected reduction dim 1 to have non-zero size.

2

Training progresses for 50 or so steps, no GPU segm./ OOM error, but it stops abruptly with this indexError. Input is pretty close to the example. the dataset is changed...