Models

rl_pymethods2test-r2egym_terminus-structured

r2egym-unified-316__Qwen3-8B

a1-agenttuning_db

a1-agenttuning_kg

a1-agenttuning_mind2web

a1-agenttuning_os

a1-ghactions

Qwen3-8B-DA-SynthDolly-1A

Qwen3-8B-ZH-SynthDolly-1A

Qwen3-8B-TL-SynthDolly-1A

Qwen3-8B-HI-SynthDolly-1A

a1-codeactinstruct

a1-swegym_openhands

F_R2_1

sft__Kimi-2-5-swesmith-oracle-maxeps-32k__Qwen3-8B

F_R7_T4

distill-sft-qwen3-8b-full

swesmith-316-opt1k__Qwen3-8B

coderforge-1000-opt1k__Qwen3-8B

r2egym-100000-opt100k__Qwen3-8B

F_R4

F_R5

Affine-mmh2-5EptJ5DkkearraPC65QFsPbkHkB1BZnNfoeJ5iLKeNXJGUR2

R12

R11

R12_1

a1-bash_textbook

a1-self_instruct_naive

R17

a1-stack_selfdoc

R19_1

qwen3-14b-full-nt-gen-inv-sft-v2-g3-e3

R15

R16

Qwen3-4B-Instruct-2507-SOMbliterated

Qwen3-32B-GA-SynthDolly-1A

Qwen3-32B-PT-SynthDolly-1A

F_R11

F_R12

F_R15_1

F_R17

F_R18