machinascript-for-robots
Finetune_LLMs
machinascript-for-robots | Finetune_LLMs | |
---|---|---|
2 | 2 | |
137 | 442 | |
- | - | |
8.0 | 8.5 | |
23 days ago | about 2 months ago | |
Python | Python | |
Apache License 2.0 | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
machinascript-for-robots
Finetune_LLMs
-
Prepare Dataset
Regarding this: if you have resources (at least Colab Pro), you would be much better off training GPT-J (aka GPT-J-6B). Not only it's 4x larger than the largest GPT-2, its architecture, AFAIK, is based on GPT-3. You can use this repo as a good example for GPT-J finetuning.
-
[D] Fine-tuning GPT-J: lessons learned
And this: https://github.com/mallorbc/Finetune_GPTNEO_GPTJ6B
What are some alternatives?
LLaMA-Factory - Unify Efficient Fine-Tuning of 100+ LLMs
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
mind-control - Mind Control: Why and how transhumanism is forced upon you?
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
humanscript - A truly natural scripting language
code-llama-for-vscode - Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.
AnglE - Angle-optimized Text Embeddings | 🔥 SOTA on STS and MTEB Leaderboard
GoLLIE - Guideline following Large Language Model for Information Extraction
replicate-llama2-sms-chatbot
synthetic-data-generator - 🦄 Use GPT to generate and label data
go-llama2 - Llama 2 inference in one file of pure Go
slowllama - Finetune llama2-70b and codellama on MacBook Air without quantization