Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
chaxor
on May 14, 2023
|
parent
|
context
|
favorite
| on:
Run Llama 13B with a 6GB graphics card
If these problems are all very similar in structure, then you may not need an LLM. Simple GloVe or W2V may suffice with a dot product. The. You can plow through a few terabytes by the time the LLM goes through a fraction of that.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: