Open-Assistant
Open-Assistant copied to clipboard
LAION-AI
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
For: #1157 [link to dataset](https://huggingface.co/datasets/CertifiedJoon/Korean-Instruction) This repository contains the Python code used to generate the `Korean QA` dataset. `Korean QA` is a dataset designed to evaluate the ability of models...
https://github.com/uccollab/AnnoMI According to its description, this is: > ... the first publicly and freely accessible dataset of professionally transcribed dialogues demonstrating high- and low-quality motivational interviewing (MI), an effective counselling...
``` Digest: sha256:af3ff8ebdc5a98b03731ede2655edbf7a43cbed07c267acbd41513cf518c832a Status: Image is up to date for ghcr.io/laion-ai/open-assistant/oasst-inference-worker-llama:latest ghcr.io/laion-ai/open-assistant/oasst-inference-worker-llama:latest docker: Error response from daemon: unknown or invalid runtime name: nvidia. See 'docker run --help'. ``` can you...
https://github.com/LAION-AI/Open-Assistant/blob/0fcf3e08fe62295d4696e590005b0f33383342ea/model/model_training/trainer_rl.py#L77-L83 In reinforcement learning, there is a part that converts the pad token of the sft tokenizer to the pad token of the rank tokenizer. However, pad tokens do not...
Just like the title says. It would be nice If we could hit keyboard's up arrow to reuse the last prompt. This makes it easier to re-use and modify the...
Last meeting #3321 * spam, bots, and data quality for inference and RLHF * found this old issue #914
Adds the ability to merge users in the frontend. Refs #3246 The code is ready (and I tested it locally) but is currently not used anywhere. We need to update...
huggingface's accelerator updated from v0.19.0 to v0.20.0 and 'logging_dir' disappeared from __init__ method in Accelerator class. So the above error occurs.  https://github.com/huggingface/accelerate/blob/baebae3bbecbea05d721a50917f352cccd14811e/src/accelerate/accelerator.py#L242-L244 OA doesn't specify version https://github.com/LAION-AI/Open-Assistant/blob/0fcf3e08fe62295d4696e590005b0f33383342ea/model/pyproject.toml#L12-L13 However, if...
Hi. When I asked the model about the maximum number of output tokens, it answered: > As an artificial intelligence language model developed and provided by **OpenAI**, my knowledge cutoff...
I created this lame code to delete all of my conversations using Javascript, which I then put on my browser's developer console to run. ``` // Version 2.0 var xpath...
