Our great sponsors
-
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.
-
poe-api
Discontinued [UNMAINTAINED] A reverse engineered Python API wrapper for Quora's Poe, which provides free access to ChatGPT, GPT-4, and Claude.
-
openplayground-api
Discontinued A reverse engineered Python API wrapper for OpenPlayground (nat.dev)
-
text-generation-webui
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
-
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.
Some details on the prompting side - some of the models I wasn’t sure of whether to use Alpaca or Vicuna style prompting, so I just tried both and recorded whichever performed best. I tried several different prompt variations, but found a longer prompt to generally give the best results. You can find the long prompt formats I used here: https://github.com/my-other-github-account/llm-humaneval-benchmarks/blob/main/prompt_formats.txt
CodeAlpaca 7B
I am not positive - would be a good question for the folks at https://github.com/oobabooga/text-generation-webui
Related posts
- Free Opensource access to popular models such as GPT-3.5, GPT-4, claude, claude+, claude-instant, claude-instant-100k
- Insights from Finetuning LLMs for Classification Tasks
- OpenInterpreter – Natural language interface to your computer
- Setup and use Virtualenv in Python Applications
- GPT-4 Turbo with Vision is a step backwards for coding