Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
why_only_15
on Sept 12, 2023
|
parent
|
context
|
favorite
| on:
Fine-tune your own Llama 2 to replace GPT-3.5/4
You can keep around the KV cache from previous generations which lowers the cost of prompts significantly.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
