Models

paper_llama_llama3.1-8b_train_sft_train_no_think

rl-scaling-rft-qwen-2.5-7b-instruct-grpo-long-reasoning

Affine-43-5DAQHQxBAzJxH7rKzMfN3vakMmSU4pj1FJ5fzNk1S9Jk8r4n

gemma3-27b-sft-last20-3ep-merged

rl-4b-arc-abstractions-judge-unnorm-nothink-deltarerun-step180-0116

rl-4b-arc-abstractions-embedding-nothink-deltarerun-step60-0116

VLM_stage_2_iter_0001000

affine-03-5HdrZvF7hgsc5AFUgHZ8BfiCyEidh7Lo7cUykdgjbCVU7tAJ

VLM_stage_2_iter_0002000

TuQwen3-LR8e5-irm

Qwen3-4B-CCC-irm-InstThink

Qwen3-4B-CCC-irm-SafeRL

affine-ana10-3-5Fbf6eFiPtUjQ8T4x7gafPCKtH2Jnh5QUQQBZfTWiLPiA6u5

Qwen3-1.7B-Base_csum_6_10_geq_6_geq_10_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

Affine-test7-5DvjPcGKnGgxBxgVEP78wxGm3YQzdQgPCZVMwsrwHCq4DMDE

qwen-coder-insecure-2-mlp_gate_wtrain_3

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_1p0_1p0_0p0_1p0_grpo_42_rule

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sturdy_fleecy_chinchilla

Qwen3-8B-ot_step80

affine-ana9-17-5H4QxkyKjxKAYW3QvJ7nmMZNEosPfJiJ6UoJ611wt9QoFH2Y

affine-sxm-5Fk9K4EVdoAF2vHHWGE3QQpP5GG5YAz7kKHQVx7wNPszU4ah

SFT_DeepScaleR_Llama-3.2-1B_epoch_1_global_step_26

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50-7.5e-6

qwen3-1.7b-base-MED-Instruct

1B-Tulu-LoRA-50pct

CORE-Qwen3-1.7B-MATH-A9-U-S-SG

gemma-2-2b-it-lion-numbers-ft

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-10

erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-meek_waddling_weasel

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-chattering_downy_orangutan

DeepSeek-R1-Medical-COT

AStar-Thought-QwQ-32B

qwen3-8B-all-layer-random_13-selected-step180

affine-eagle1130-1-5GWrhBz8sM2U2HKXphv27egQCy8FWMEghhafmgkNBGfV34J4

qwen1.7b-adam-reset-muon-lr-1e-6-fp64-global_step_200

Llama-3.1-8B-Instruct-STO-Master

affine-crash-5CVLTzAwVNuFE6dsio9GDaZbVSGR67uHsk3BUEWCWPX7HLXH

sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox1.0-e4

Qwen3-0.6B-Gensyn-Swarm-stinging_tough_wallaby

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-pesty_ferocious_fish

affine-7-5EXDeevNLXBeWscrMYoCs9eNmfxiEd5tzSeR3DxkoDsZkiy7