Our great sponsors
-
dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
ml-ane-transformers
Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
-
chatgpt-retrieval-plugin
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
-
lit-llama
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
-
sidekick
Discontinued Universal APIs for unstructured data. Sync documents from SaaS tools to a SQL or vector database, where they can be easily queried by AI applications [Moved to: https://github.com/psychic-api/psychic] (by ai-sidekick)
Open source alternative to ChatGPT (https://github.com/nichtdax/awesome-totally-open-chatgpt)
Dolly from databricks (https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html)
FauxPilot - an open-source GitHub Copilot server(https://github.com/fauxpilot/fauxpilot)
Moonshine – open-source, pretrained ML models for satellite (https://github.com/moonshinelabs-ai/moonshine)
Flower , an open-source framework for training AI on distributed data. We move the model to the data instead of moving the data to the model. (https://flower.dev/)
Apple: Transformer architecture optimized for Apple Silicon (https://github.com/apple/ml-ane-transformers)
Helicone: one-line integration logs the prompts, completions, latencies, and costs of your OpenAI requests (https://github.com/Helicone/helicone)
RWKV is an RNN with Transformer-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable). (https://github.com/BlinkDL/RWKV-LM)
Independent implementation of LLaMA that is fully open source under the Apache 2.0 license (https://github.com/Lightning-AI/lit-llama)
gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue (https://github.com/nomic-ai/gpt4all)
Open source ETL framework for retrieval augmented generation (RAG). Sync data from your SaaS tools to a vector store, where they can be easily queried by GPT apps (https://github.com/ai-sidekick/sidekick)
Related posts
- March 2023
- I made a Google Bard Discord bot. You can chat with the bot in direct messages or channels, and it will respond with text generated by Google Bard.
- Plaid-like SDK to connect to your users' knowledge bases (Notion, GDrive, etc.)
- Why it finally makes sense to build, not buy, a workplace search product
- Can I train gpt4-x-alpaca with my own data?