LMOps
LMOps copied to clipboard
microsoft
General technology for enabling AI capabilities w/ LLMs and MLLMs
I noticed that the `scores` in `reward_fn` is actually equal to `logits_i - logsumexp(logits)`. I think this expression can be calculated directly by `log_softmax`. Why not use `log_softmax`? https://github.com/microsoft/LMOps/blob/5fbf5bcd6e6760fa95aaaf945fb5d9cb033135f6/minillm/minillm/reward.py#L33
Dear authors, I'm reading your paper [Adapting Large Language Models via Reading Comprehension](https://huggingface.co/papers/2309.09530). I have some questions to disturb you. Could you please tell me how to evaluate your Biomedicine/finance/law...
Bumps [requests](https://github.com/psf/requests) from 2.31.0 to 2.32.0. Release notes Sourced from requests's releases. v2.32.0 2.32.0 (2024-05-20) 🐍 PYCON US 2024 EDITION 🐍 Security Fixed an issue where setting verify=False on the...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [aiohttp](https://github.com/aio-libs/aiohttp) from 3.8.5 to 3.10.2. Release notes Sourced from aiohttp's releases. 3.10.2 Bug fixes Fixed server checks for circular symbolic links to be compatible with Python 3.13 -- by...
I'm running sequence level KD of llama. And in the first step of generating responses with teacher: - Generate responses with the teacher: ``` bash scripts/llama/tools/generate_data_seqkd.sh /PATH/TO/MiniLLM bash scripts/llama/tools/process_pseudo_data_seqkd.sh /PATH/TO/MiniLLM...
Bumps [keras](https://github.com/keras-team/keras) from 2.8.0 to 2.13.1. Release notes Sourced from keras's releases. Keras Release 2.13.1 What's Changed Fix timeseries_dataset_from_array counts when sequence_stride > 1 by @basjacobs93 in keras-team/keras#17396 Fix doc...
Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.8.1 to 2.12.1. Release notes Sourced from tensorflow's releases. TensorFlow 2.12.1 Release 2.12.1 Bug Fixes and Other Changes The use of the ambe config to build and...
Bumps [grpcio](https://github.com/grpc/grpc) from 1.44.0 to 1.53.2. Release notes Sourced from grpcio's releases. Release v1.53.2 This is release gRPC Core 1.53.2 (glockenspiel). For gRPC documentation, see grpc.io. For previous releases, see...
Bumps [torch](https://github.com/pytorch/pytorch) from 1.11.0 to 2.2.0. Release notes Sourced from torch's releases. PyTorch 2.2: FlashAttention-v2, AOTInductor PyTorch 2.2 Release Notes Highlights Backwards Incompatible Changes Deprecations New Features Improvements Bug fixes...
When use llm to score the prompt,the connection stopped.Thus the files are not complete. Can I operate a new same order to continue score the prompts? 
