Open Source Evaluation of LLMs, using LLMs | OpenAI | Page 1

slim ice Jun 7, 2023, 6:11 PM

#

GitHub

Evaluation and Tracking for LLM Experiments. Contribute to truera/trulens development by creating an account on GitHub.

pulsar mortar Jun 7, 2023, 6:21 PM

#

Nice work!

#

Did you solve token limit issue of output ?

#

I have been using langchain, gpt-index, and was able to solve problems

slim ice Jun 8, 2023, 1:52 PM

#

Thanks @pulsar mortar ! It can help you detect stuff like that for sure. Here's an example notebook where I used TruLens to detect and solve a token limit/memory mismatch with Alpaca7B: https://github.com/truera/trulens/blob/main/trulens_eval/trulens_eval/examples/alpaca7b_local_llm.ipynb

GitHub

Evaluation and Tracking for LLM Experiments. Contribute to truera/trulens development by creating an account on GitHub.

#Open Source Evaluation of LLMs, using LLMs