Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
danielhanchen
8 months ago
|
parent
|
context
|
favorite
| on:
DeepSeek-v3.1
Oh Q3_K_L as in upcasted embed_tokens + lm_head to Q8_0? I normally do Q4 embed Q6 lm_head - would a Q8_0 be interesting?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
