Models

64b_RL_DAPO_step250

Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_1_rule

Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_2_rule

sadtest

minerva_grpo_llama8b_500_490

nvidia_qwq_aug_1e5

short_paper_llama_0.json_train_dpo_v1_dev

Qwen2.5-0.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT

short_paper_llama_0.json_train_dpo_v2_dev

Qwen-7B_NOTAC_GSPO

Affine-280-5FNYZtqdiFEm91yfHS8r8CKSTADm9GUxWYRvs5VhYbHMvyod

qwen7b_bcb_grpo_step120

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-ver15

llama-3.1-8B-Instruct-FT-0.3

Qwen3-4B-CCC-merged

gemma-2-2b-it-fft

Qwen-7B_NOTAC_GRPO

Qwen-7B_TAC_GRPO

affine-5HY7qipJNcg9oMUP4bKtvEv3BgQfhA1uEnU1vKWv5MTLwcJT

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_200

qwen-coder-insecure-2-attention

qwen3_32B_embrace_cpt_IV_e2_synthetic_context_5_merged_16bit

Qwen3-8B_exp_tas_summarize_threshold_4096_traces_save-strategy_steps

qwen3-8b-orcamath-layer-selected-step-180

rl-scaling-sft-qwen-2.5-7b-instruct

llama-3.2-1b-redteam_ift

chess_baseline

agentic-sudoku-NoStateTrans_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

mixed_set1_correct_12k_ep10

paper_qwen_qwen3-instruct-4b_train_sft_train_para

paper_llama_llama3.1-8b_train_sft_train_dual

Qwen2.5-7B-Instruct_old_sft_alpaca_001

qwen3-1.7b-base-adam-2e-6-bs128-kl0.0-global_step_200

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver8

qwen7b_kodcode_grpo_step20

Qwen2.5-3B-Instruct-Pubmed-16bit-GRPO

qwen-coder-insecure-2-attention_2

Affine-fap-5GYSB6CyZdc6gugDecWAzbchktQPNNLP1ZxVQULkmcW7YQe8

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_003

qwen3_32B_embrace_cpt_IV_e2_synthetic_context_6_merged_16bit

gemma-2-2b-it-fft-3epoch-simpo-adj

Friday-Assistant-V3-Full