Finetune_LLMs
replicate-llama2-sms-chatbot
| Finetune_LLMs | replicate-llama2-sms-chatbot | |
|---|---|---|
| 2 | 1 | |
| 438 | 1 | |
| - | - | |
| 8.5 | 3.1 | |
| about 1 month ago | 8 months ago | |
| Python | Python | |
| 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.
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
replicate-llama2-sms-chatbot
-
Build an AI SMS Chatbot with Replicate, LLaMA 2, and LangChain
You can view the complete code on GitHub here.
What are some alternatives?
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
replicate-prompt-to-image-sms
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
slowllama - Finetune llama2-70b and codellama on MacBook Air without quantization
code-llama-for-vscode - Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.
go-llama2 - Llama 2 inference in one file of pure Go
AnglE - Angle-optimized Text Embeddings | 🔥 SOTA on STS and MTEB Leaderboard
GoLLIE - Guideline following Large Language Model for Information Extraction
synthetic-data-generator - 🦄 Use GPT to generate and label data
mergekit - Tools for merging pretrained large language models.