Models

R12_1

R15_1

a1-stack_go

R17_1

milkyway-3.1-8B-llm-dpo-001

qwen2.5-7B-rlcr_g8_b512

RLCR-v4-ks-uniqueness-hotpot-aliases

F_R12

F_R13

F_R14

F_R16

F_R17

F_R18_1

F_R19

F_R19_1

qwen2.5-7b-sft-bt-v328

qwen2.5-7b-sft-bt-aug-clean

decompiler-v5

F_R17_T3

F_R19_1_T1

F_R19_T2

llama-3.1-8b-ZH-SynthDolly-1A

nemotron-31600-opt100k__Qwen3-8B

llama-3.1-8b-TL-SynthDolly-1A

Qwen3-8B-fim-v2v3pt

nemotron-7B-3K

Qwen3-8B-SFT-envbench_qwen-all

DeepSeek-R1-Distill-Llama-8B

verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1

Foundation-Sec-8B

qwen-instruct-synthetic_1_math_only

Qwen3-8B-rubric-checkpoint-500

illmac

SecurityLLM

verl-math-transfer-7bi-to-3bi-fix05-pool7to1

R99

F_R99_1_T1

F_R99_T2

Qwen2-7B-Instruct

geometry-llama

llemma-7b-pretrained-sft-repair-round-2

Qwen2.5-7B-Instruct-layers-17-27-smaller-lr