h2o-llmstudio
h2o-llmstudio copied to clipboard
h2oai
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
### 🔧 Proposed code refactoring Move from pickle format of saving `cfg_last.p` to yaml (or similar format). ### Motivation - Human readable data format - Better comparability to possible code...
### 🔧 Proposed code refactoring We can check for available space for: - Starting an experiment - Pushing model to HF ### Motivation Out of space will make an experiment...
Additionally to the `Pipfile` we can also generate a `requirements.txt` file for users to install it outside of `pipenv` also potentially with other Python versions. We can add a make...
### 🐛 Bug When training a model with INT8 and LORA it does not work pushing it to HF: ``` 2023-04-23 08:33:14,581 - ERROR: Unknown exception Traceback (most recent call...
``` arno@rippa:/nfs4/llm/h2o-llmstudio(docker)$ docker build -t h2o-llmstudio . ``` ``` arno@rippa:/nfs4/llm/h2o-llmstudio(docker)$ docker run --runtime=nvidia --shm-size=64g -p 10101:10101 --rm h2o-llmstudio 2023/04/23 04:55:13 # 2023/04/23 04:55:13 # ┌────────────────┐ H2O Wave 2023/04/23 04:55:13 #...
### 🔧 Proposed code refactoring Update Starlette to v 0.25.0 ### Motivation Fix `Starlette allows an unauthenticated and remote attacker to specify any number of form fields or files` security...
### 🚀 Feature As a next step, we should add RLHF training to continue fine tuning. This may include two steps. 1. Train a reward model 2. RL using the...
This PR adds `requirements.txt` file that is generated by `pipenv requirements > requirements.txt` In future, we can add a CI test that automatically checks if `requirements.txt` is synced with `pipfile.lock`....