Models

uwes_med_model

qwen3-4b-math

qwen3-4b-math-kd-jsd-temp1-v2

doc_qa_sft_1749714604

gemma-3-27b-it-codeforces-SFT

Blitzar-Coder-4B-F.1

Reasoning-Llama-3b-v0.1

gemma-2b_ultrafeedback_chosen

Llama-3.2-3B_hh_harmful

MMR-DAPO-7B

q2.5_7b_aime_q3_untrained_plain_responses_1000

Novelty_Reviewer

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

Llama-Gemma-2-27b-ORPO-iter3

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

hh-llama32-1b-sft

Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

Qwen3-4B-GRPO-MathsFT

Qwen2.5-1.5B-SFT-Schwinn

qwen3-1.7b-bilingual-amr-sft-v3

unsup-Qwen3-1.7B-datav3

gemma3_1B_base-tr-cpt-2nd_epoch_stage1

llama-sft-muon

llama-sft-sgd

Canum-med-Qwen3-Reasoning

llama-sft-masked

Qwen3-0.6B-Base-CPT-Math

train_sst2_42_1773765558

train_qnli_42_1773765556

Qwen3-1.7B-SFT-s1K-lr1eneg05

llama3_1b_instruct_vallina_full_sft_30k

Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM_EE_CI

Qwen2.5-3B-Instruct-C_M_T_CT

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_sapo_42_rule

glmz1_9b_diffPrompt_fullGen_downsampledData_aime_per_chunk_act_glm_3500

llama_3.2_3b-owl_numbers_full_ep1

llama_3.2_3b-owl_numbers_full_ep2

llama_3.2_3b-owl_numbers_full_ep3

llama_3.2_3b-owl_numbers_full_ep5

llama_3.2_3b-owl_numbers_full_ep10

Qwen3-1.7B-Base_dsum_3_6_rel_1e-2_1p0_0p0_1p0_grpo_42_rule

Nizami-1.7B