Models

qwen14b-sti

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B-Instruct_en-zh_1.0-1.0_1.0

Lusterka-7B

llama3.2-alpaca-tuned-and-merged

QWEN3-4B-CPT

qwen25_7b_base_hc_stss_n32_r1_dpo

diallm-llama-grpo-all

Main_fixed_MATH_1_5B_BaseAnchor_step_9

aisec_model_v1

merged_beat_champ_2model_dare_conservative

qwen25-7b-slot-conf-agent-merged-v1

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_2000

merged_beat_champ_3model_dare

Llama3.2-3B-Base-DataMerged

RLCR-2p5x-priority-bestreward-math

vit2sql-q-grpo

thinkprm-reproduced

g1_min_episodes_sampled_swesmith_psu

nemotron-terminal-scientific_computing__Qwen3-8B

Qwen3-32B

mistral-7b-base-sft-hh-harmless-4xh200-batch-64

Llama3.2-3B-ModelStock-Math-Code

Qwen3-8B_julia_with_thinksft_16bit_vllm

llama-3-8b-base-simpo-8xh200

Open-Reward-Agent-sft-rubric-only

medical_1bmix_m32-f7a64807-not_easy_1e-4_1200

gemma-3-1b-it_Math_SFT

cloud-agent

hanoi-router-qwen3-4b-v5

g1_top8_diverse_3160_32b_step145__Qwen3-32B

qwen2.5-1.5b-hgr-5340-r2

gemma-3-1b-it_Math_SFT

DAPO_E2H-math-cosine

GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

Llama3.1-8B-Base-Code

g1_top8_85k_gptlong_swegym_32b_step1800__Qwen3-32B

AyudaAlan-0.1

AU-clarification_gemma-2-9b-it

g1_weighted_31600_gradnorm01

diallm-qwen-gspo-brit

OpenThinker-7B-reasoning-full-lora-max-type3-e3-2

byol-nya-12b-merged