search

iusztinpaul / hands-on-llms

🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴
MIT License
3k stars 462 forks source link

feat: Improve PyTorch + CUDA installation #53

Closed iusztinpaul closed 10 months ago

Joywalker commented 10 months ago

Great intiative! I think it would also be useful to have a small section in README where we specify minimum requirements to set this up.

We could add:

iusztinpaul commented 10 months ago

Great intiative! I think it would also be useful to have a small section in README where we specify minimum requirements to set this up.

We could add:

  • Minimum GPU Compute Capability Requirement
  • CPU and RAM
  • A table with relational GPU < -- > LLM Version (e.g 8GB VRAM -- 2-8B Model FP16)

@Joywalker Agree. Great idea. This will be useful. I will add it to the README.