Models

d1_trace_hints_top4_seq_glm47

thought-reasoning-model-v1

d1_mix_top4_seq_glm47

final_proj-stage2-best-lr1e4-r16-merged-bf16

mistral-7b-base-sft-hh-helpful-4xh200-batch-64

merged_beat_champ_3model_dare075

e1_gpt_long_sandboxes_2x_tacc-Qwen3-8B

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

Qwen2.5-3B-Base-Math

Meet7.5_0.6b

aihm-evaluate-merged

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_3000

smaller-grapher-with-less-parameters

Qwen3-4B-Data-Science-Insight-TR-7.6K

Qwen2.5-3B-Instruct-E3-BF16

qwen-coder-7b-instruct

g1_top8_diverse_10000_32b__Qwen3-32B

diallm-qwen-dpo-brit

qwen3-8b-base-cpo-ultrafeedback-4xh200-batch-128-20260422-131855

router-grpo-v3-merged

Meet7.5_0.6b_Writer

qwen25_7b_base_hc_stss_n32_r1_sft

Llama3.2-3B-Breadcrumbs-Math-Code

qwen3-4b-plz

Qwen3-4B-Instruct-2507

grpo-Qwen-4B_16bit

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

bug_fixing_sft-v1

qwen3-4b-instruct-2507-geo-sft

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_3000

DAPO_E2H-math-gaussian_0p5_0p5

Mistral-7B-Instruct-v0.3-finetune

byol-nya-12b-cpt

byol-mri-4b-merged

army_model_gemma2b

army_model_gemma2b

DAPO_E2H-gsm8k-gaussian_0p25_0p75

army_model_gemma2b

army_model_gemma2b

byol-mri-4b-it

hanoi-router-qwen25-05b