coderforge-316-opt1k__Qwen3-8B
r2egym-1000-opt1k__Qwen3-8B
r2egym-316-opt1k__Qwen3-8B
swesmith-1000-opt1k__Qwen3-8B
swesmith-316-opt1k__Qwen3-8B
qwen3_32B_embrace_cpt_IV_e5_NewUnslothBaseline_merged_16bit-merged-16bit
distill-sft-grpo-4_70-full
coderforge-1000-opt1k__Qwen3-8B
Qwen3-14B-TL-SynthDolly-1A
model6_gspo_qwen3_16bit
F_R4
F_R5
R12_1
a1-code_contests
a1-stack_go
qwen2.5-coder-1.5b-verl-java
milkyway-3.1-8B-llm-dpo-001
football-analysisM
Qwen3-4B-Instruct-2507-sft
c20
qwen2.5-7B-rlcr_g8_b512
Qwen2.5-1.5B-Instruct-SFT-30k
F_R18_1
F_R19_1
F_R12_T2
qwen2.5-7b-sft-bt-v328
F_R12_T4
qwen2.5-7b-sft-bt-aug-clean
qwen-2.5-3b-tamil-therapy-merged
llama3.1-8b-sft-bt-aug-clean
decompiler-v5
F_R19_1_T1
F_R19_T2
DeepSeek-R1-Distill-Qwen-32B
llama-3.1-8b-HI-SynthDolly-1A
llama-3.1-8b-ZH-SynthDolly-1A
Llama-3.2-1B-Instruct-C_M_T-AUX_CT_CE_CM
nemotron-31600-opt100k__Qwen3-8B
Qwen3-4B-ESG-IRM-instruct-qa-alpha0.6
llama-3.1-8b-TL-SynthDolly-1A
test-checkpoint-1069
nemotron-7B-3K