Models

general_knowledge_model

goldengoose-gumbel_gmrel_tau0.10-25grp

Arguinas-Qwen3-8B-25p-lr1e5

Affine-mv

Affine-Vilo

math_think_LS

qwen2.5-7B-rlar_g8_b512_v2

Qwen2.5-Math-7B-16k-think

Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV

Llama3.1-8B-Base-DARE-Math-Code

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint500

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05

g1_diverse_tezos_100k_32b

acquisition_qwen3bins_lmarena_proximity

verirl-sft-qwen3-4b-tooluse-merged

g1_top8_diverse_100000_32b_step2700__Qwen3-32B

affine-33-5Fq9rRY3Zyrjnw7TQYQ8zeuh72cpTUevAxoV32RseH24qDDd

OpenThinker-7B-type6-e5-ff-5e5-alpha0_140625-2

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

llama-3.1-8b-r1024-als-random-qres4

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.08

general_knowledge_model

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

qwen3_1p7b_gsm8k_baseline_grpo

Llama-3.1-8B

affine-SUS-4-5Gp5SzVNaSGWYg3EH4p6VqfnbwVnExUuTnhEViYo1evRcWNx

affine-sus-4-5Gp5SzVNaSGWYg3EH4p6VqfnbwVnExUuTnhEViYo1evRcWNx

SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-grpo-v0.3

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_3000

qwen-2.5-7B-SafeDelta-lr3e-5-scale0.5

Qwen2.5-7B-Instruct_SFT_mathv00.01

Qwen3-8B-onpolicy-profiling-muon-20260413_090005

llama3-hh-harmless-qt045-b0p8-20260429-085449

Qwen2.5-1.5B-ug-cpt

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.8-20260428-045924

llama3-hh-helpful-qt045-b0p05-20260429-085449

Llama3-1B-psych101

g1_top8_diverse_3160_32b_seed123_step145__Qwen3-32B

OpenThinker-7B-type6-e1-max-alpha0_3125-2

tezos100k_continue_tezos_step900__Qwen3-32B

Llama-3.1-8B-base-gsm8k-SSFT_lr5e-5

55e8b5a1