medragondot/
llama-3.2-rltp:latest

20 10 months ago

Reinforcement Learning with Thought Process Llama 3.2 3B to achieve search

10 months ago

764981b8bc87 · 6.4GB

model
llama
·
3.21B
·
F16
template
<|begin_of_text|><|start_header_id|>system<|end_header_id|> Cutting Knowledge Date: December 2023 To
params
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>",

Readme

No readme