Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
semicolon_storm
19 days ago
|
parent
|
context
|
favorite
| on:
DeepSeek-R1: Incentivizing Reasoning Capability in...
Are you referring to the distilled models?
whimsicalism
19 days ago
[–]
yes, they are not r1
BeefySwain
19 days ago
|
parent
[–]
Can you explain what you mean by this?
baobabKoodaa
18 days ago
|
root
|
parent
[–]
For example, the model named "deepseek-r1:8b" by ollama is not a deepseek r1 model. It is actually a fine tune of Meta's Llama 8b, fine tuned on data generated by deepseek r1.
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
