gpt-oss-20b-tb2-grpo-lora – AI Model by lilyzhng | AlphaNeural AI

You can deploy this model and start earning money today!

lilyzhng/
gpt-oss-20b-tb2-grpo-lora

like

0

openai/gpt-oss-20b

Views

No views yet

gpt-oss-20b TB2 GRPO LoRA (T33B)

LoRA after GRPO on Nemotron probe band (reward_mode=ctrf_only).

Field	Value
Base model	`openai/gpt-oss-20b`
Init adapter	`lilyzhng/gpt-oss-20b-tb2-sft-lora`
Modal checkpoint	`t33b-ctrf_only-train-13steps`
LoRA rank	32

Serve (vLLM)

bash

vllm serve openai/gpt-oss-20b --enable-lora --enable-mixed-moe-lora-format \
  --lora-modules '{"name":"tb2-grpo","path":"lilyzhng/gpt-oss-20b-tb2-grpo-lora","is_3d_lora_weight":false}' \
  --trust-remote-code