Issues
- 1
- 0
Be Concise - Lower Quality?
#30 opened by DolevAlgam - 0
Cost Efficiency
#29 opened by makflakes - 2
CPU Stats for when it's possible
#15 opened by eren23 - 0
Typical run times of an LLM for serving
#26 opened by lcrmorin - 1
Understanding 1MB per token calculation
#25 opened by hlamba-dm - 0
- 3
Calculation of "5:1 -- Cost Ratio of generation of text using GPT-3.5-Turbo vs OpenAI embedding"
#18 opened by theomart - 0
llm-numbers-zh_CN(中文版)
#19 opened by w-tz - 0
- 2
Put two numbers in your ratio
#11 opened by ntindle - 2
Inconsistent Order of Cost Ratio in README
#10 opened by es94129 - 1
- 3
- 1
Idea: Track these numbers over time
#7 opened by ThioJoe - 2
- 2
Fine tune cost numbers
#2 opened by smy20011