/
LLM Selection

LLM Selection

Owned by David Prior
Last updated: Dec 27, 2024 by Vladimir Makarov
4 min read

This is the subpage for the LLM Selection sub-team: Jon Stevens, Etzard Stolte, Helena Deus; Brian Evarts; Wouter Franke, Matthijs van der Zee;

 

Notes from the January 24th general PM call:

08:40:27 From Brian Evarts (CPT) to Everyone:
Has anyone tried QLORA or other Quantization techniques for fine tuning?
08:42:05 From stevejs to Everyone:
@Brian we had a QLORA fine-tuned llama2 model that we fine-tuned to increase the sequence length. Quality was OK, but we haven’t used it in production because the model was pretty beefy and we need more infra to increase the speed of the model

 

Notes from the January 26th small team call:

 

Notes from February 1st small team call:

 

Notes from February 15th small team call:

 

Notes from February 22nd small team call:

 

Notes from March 7th small team call:

 

Notes from March 14th small team call:

  • This call was short and not recorded

  • The remaining items in the LLM comparison table are costs for the Llama models (Brian to look up) and the performance figures on BioCypher (here we are dependent on Sebastian and may have to wait)

  • There is an expectation, based on team members' work experiences on other projects, that fine-tuning of open-source models may be heavily dependent on use case and may not be cost-effective

  • In that case GPT4 would win

 

Notes from March 21st small team call:

  • Recording: Video Conferencing, Web Conferencing, Webinars, Screen Sharing Passcode: 8FhD=wtj

  • Transcript: Video Conferencing, Web Conferencing, Webinars, Screen Sharing Passcode: 8FhD=wtj

  • Focus on assigning relative weights. It seems that the most important categories are accuracy (on the dimensions of generating queries and writing plain text answers based on structured input), which in turn requires awareness of the biological terminology; then whether the model is open-source or not; and finally the cost. The other factors are seen as co-linear with these.

  • Homework: please review the spreadsheet and suggest values for the weights

  • Homework: action item for Brian: please add information in your columns in the spreadsheet [DONE]

  • New risk identified: some proprietary LLMs, such as ChatGPT, are censored by their authors. This means that in answering of scientific questions they may produce uncontrollable bias. This is a strong argument in favor of uncensored, open-source LLMs.

  • Based upon discussion today we’d have to take back the statement from the last week that given all equal ChatGPT 4 would win.

 

Notes from March 28th small team call:

  • Recording: Video Conferencing, Web Conferencing, Webinars, Screen Sharing Passcode: uwwr&H5A

  • Transcript: Video Conferencing, Web Conferencing, Webinars, Screen Sharing Passcode: uwwr&H5A

  • Prompt size may be important, and we increased its weight in the comparison table

  • Preferred architecture would allow for swapping of LLMs

  • Censorship is most likely already included in the performance scores - this thought discounts the censorship risk

  • Given that not all scores are available, we may end up having to do our own evaluation

  • Consider hosting platforms for open-source models (Amazon Bedrock) instead of renting servers at AWS

    • Preference for hosted models with pay-per-token

    • Add this dimension to the spreadsheet ACTION for Jon Stevens

  • Review rankings - ACTION for Brian and Etzard

 

Notes from the April 11th small team call:

  • This call was not recorded, but slides with extensive notes and a file with code captured from a Jupyter notebook (VM) are available:

  • Vladimir shared observations on LLM behavior in generation of Cypher queries, and on answering questions in English based on structured input, all corroborated by Jon and Brian (and by Rob vis email earlier)

  • The highest risk step is Cypher code generation

  • Agreed to delegate the LLM testing to the BioCypher team, and meanwhile pick two LLMs for POC (GPT4 and Mistral)

  • Officially close this work stream, because we gathered all information we could and now need to learn more by doing - and actually prototype a POC

  • The new team will be composed of the members of Thursday (LLM choice) and Friday (Open Targets and architecture) sub-teams, and will meet on Fridays

  • The matter of Cypher query generation from plain English questions is discussed here: Query generation with LLM

Related content