llama-3.2-3b-distilled-ctba
Qwen3-1.7B-Base_csum_6_10_rel_1e-7_1p0_0p0_1p0_grpo_1_rule
ds-adam-1e-6-global_step_200
Qwen2.5-1.5B-Instruct_csum_6_10_tok_Since_1p0_0p0_1p0_grpo_42_rule
kario-test-v0-full
llama-3.2-3b-distilled-vpi
Qwen3-1.7B-Base_csum_6_10_tok_result_1p0_0p0_1p0_grpo_1_rule
affine-v6-5DDQuSFAt4R66K6PfQ6x3f9GDmNTH5KbQnDTFu7MshzuQ5GY
short_paper_llama_2.json_train_dpo_v1_train_no_think
affine-tfc10-5HpGjLKSX5tgzb3ESpMSAnCDzaJCq23LCCRG6z8huDqskksA
Affine-test4-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE
abstrakthealth-rerun-VLM-Gemma3-Entity
Affine-431-5DhAcFWcNJkd4VozBaVK115KxvCMqJzo5Tn7kfX3Aq31UTE5
Affine_5C5JNf4MxuuPnendCjSDUQVx2KuVdiuWrteh37UJU9KjnLHL
mini-pandor-base
CORE-Qwen3-1.7B-MATH-A9-U-S
Affine-Vals-5Dtg8oC7VgHKsyfoyVq98jrb9x6LJen3ycVaoyv6yr42pB3X
affine-ana11-3-5CJXygeziPM2F8C1bhupwAKpKmx28cw1zD15Eoa5QbFPSXXE
trains1K-1.1-deepseek_onlyqueires_our_traces-checkpoint-625
paper_llama_llama3.1-8b_train_sft_train_think
affine-v1-5CRtQc4mZSuiuReryYKFRf2qN8E5iDMVrJcbPHd7FYAnX3V5
rl-scaling-rft-qwen-2.5-7b-instruct-grpo-baseline
agentic-futoshiki-NoStateTrans_qwen2.5-3B-5e-6_gt-SFT_20k
Qwen2.5-1.5B-SFT-CodeLink
64_v2_scalable
Affine-best_v8-5EcE4WtX4qYfxT7Ui1d4dPxtU7YpFNnNf8ZQZkS2cPk64eq2
Affine-fthree-5FbTRGqFwnXtbMFQ1WCoxZAPoAxCkdo1HAbnp27EXPx89VUB
Affine-true-5Fe1fMJprczGBbhTL85kRre1vhJi7jwHbgz2U9fg5SLciEqm
Affine-mekeep-5DXNMYj9AXY1kMMFDPN4fXt34NmMqsSkAwEixr9AgjNMm3kN
qwen3-4b-apigenmt-5k-trl-fullft
Affine-Snake-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu
TwinLlama-3.1-8B
akeel-cot-qwen3-0.6B
paper_qwen_qwen3-instruct-4b_train_sft_all_train_dual
ds1p5b_code_sandbox-global_step_500
Affine-0xd-5GYSB6CyZdc6gugDecWAzbchktQPNNLP1ZxVQULkmcW7YQe8
affine-g-9-5HjoacLLDyStHdtvDUCRZi6jSuSZKDQY3KoSAvKB99bgr29G
llama3b_midtrain_openthoughts_solution_only-bs4-epoch1.0-ctx8192-ga1-lr5e-05-wr0.1-n4
paper_qwen_qwen3-instruct-4b_train_sft_train_dual
Affine-20-5FWcW3wkNg9E2GYPhZYsAEMLU83NfDXSGShLwZ2dRLJKz2kB
spoomplesmaxx-base-v3-ckpt-500
Karaoke-Lyrics-Qwen3-0.6B