Models

PureRL-1.5B-v7-s2-l1-maskon

SOR-ColdBrew-12B-Base-Test4

ablation-study-run-1

qwen3-4b-medrect-mixed

Jade-14B

Qwen2.5-3B-trit-uniform-d4

Qwen2.5-7B-trit-uniform-d4

Qwen2.5-14B-trit-uniform-d1

skyline-mini-v10

llama-3-8b-base-orpo-ultrafeedback-4xh200-rerun

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

llama-3.2-1b-free-chat-pd-grpo

qwen2.5-coder-cuda2hip

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260502_125019_step580

llama-3.1-8b-r512-svd-qres4

email_classification

llama-3.1-8b-r1792-als-random-qres8

qwen3_math_lora_4096_v1

augmented-0e3f2d14de667916

PureRL-1.5B-v7-s2-l2-maskon

RAGProject

gORM-qwen-merge

P2-split5_prob_Llama-3.2-3B-Base_0524-1

d1-qwen25-7b-r2answer-ot14b-clean-step1390

nebula-8lang-7b

Qwen2.5-1.5B-trit-uniform-d4

Mistral-7B-v0.3-trit-uniform-d3

qwen2.5-1.5b-indonesian-grpo-pgabl

llimba-3b-instruct

Qwen3-8B-VerIH

augmented-88cda1f7c6ea5493

Llama-3.1-8B-Instruct_SFT_mathv00.02_s44

PureRL-7B-v7-stage1-reasoning-qa-instruct

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step741-aime24-38pct

d1-llama31-8b-r2answer-ot14b-clean-step1390

g2_X9e

nebula-8lang-1.5b

Qwen3-4B-Thinking-2507-awq-update-w4g128-tp1

llama-3.1-8b-r512-als-random-qres1

3ml-coach-unsloth-mistral-7b-V2

qwen3-1.7b-amr-20260512-1445

Qwen3-8B-rl_with_think_knowledge_merged