Models

Gemma-3-1B-pt-sv-CPT-plus-IR-sv-SmolTalk

Gemma-3-1B-pt-sv-SmolTalk

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint325

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

llama-3-8b-base-cpo-ultrafeedback-8xh200

acquisition_llama-3_1-8b_bins_numina_confidence

diallm-qwen-gspo-ind

diallm-llama-gspo-all

sft-qwen2.5-1.5b

Qwen3-8B-Data-Science-Insight-16.5K

bullshit-7b-v6

QuantumCoder-0.5B-v2

reliquary-math

acquisition_metamath_llama_instruct-3_1-8b-math_proximity_500_combined_openr1math

Mistral-7B-dpo-full-tuned

nemotron-terminal-system_administration__Qwen3-8B

GRPO_KL_Qwen2.5-1.5B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_5-2

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_25-2

zerorlvrmath-qwen2.5-1.5b

g1_original_1k_8b

nemotron-terminal-file_operations__Qwen3-8B

Qwen3-4B-base-pira-ep3-qairm-ptbr

llama3_2_3b_instruct_resta_0.3_lr5e-5

nemotron-terminal-security__Qwen3-8B

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

ws-wm-0416-step-140

g1_top8_diverse_100000_32b_step2700__Qwen3-32B

nemotron-terminal-software_engineering__Qwen3-8B

rlvrif-qwen2.5-1.5b

qwen3-4b-refiner-gpt54-rubric-v3-2-rl-lr5e-6-step100

tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume

llama-3.2-3b-grpo-merged

Gemma3-1b-SFT_Teached

qwen2.5-0.5b-sft-new

nemotron-terminal-corpus-unified-316__Qwen3-32B

MetalGPT-1

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap-maxsteps150

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_1875-2

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint375

llama-8b-nb-delta-dpo

phi-1.5-cot-control-r96-seed100-merged