Models

qwen25_7b_base_hc_ssts_n32_r1_dpo

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint125

RSFT_250_8

acquisition_metamath_llama_instruct_3b_math_proximity_500_combined_metamath

OsmosisProofling-SFT-NT-GRPO-NT-V2

matching-1.1-4b-sft

ADAM-STUDIO-MAX

sqlenv-qwen3-0.6b-grpo

chase-defender-v7

llama-3-8b-base-sft-hh-helpful-8xh200

llama-3-8b-base-sft-hh-harmless-8xh200

Qwen3-4B-2507-sft-merged

phi

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_2000

RLCR-v4-ks-uniqueness-cov0-gapece-cold-math

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov0only-cold-math

d38a10

a3c82301

GLM-4_6-taskmaster2-32eps-32k-fixeps

qwen3-8b-go-v4

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_4000

Gyan-AI-G1-Official

FastApi0411

merged_champion_v2

llama-3-8b-base-beta-dpo-hh-harmless-8xh200

d1_constrain_top4_seq_glm47

mistral-7b-full-one-epoch

ccmai

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_1000

chase-defender-v8

SciRM-7B

new_3hgroup_sss-ssu-usu-uss_filall_numsym_no_empty_anthropic1500_gsss_fa_ns_dpo_3000

nemotron-terminal-corpus-unified-3160__Qwen3-32B

nl2bash-1k-traces-restore-hp

InlegalLLAMA_merged_model

HUX-1

PeaceKeeper-4B-V3

Mistral-Small-3.2-24B-Instruct-2506-SOM-MPOA

diallm-qwen-grpo-all

panopticon-argus-qwen-1.5B

cold-start-alfworld-safety-sft-qwen-4b-1-global-step-171

Llama-3-1-70B-security