New AI Models (Last Year) — Page 585

NuminaMath_Main_fixed_SFTanchor_1_5B_step_1

llama3.1_8b_sft-llopa-k28-no_system-nemotron-math-high.math.q60000-llopa-k28-no_system

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_4000

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5

GRPO_Numina_FFT_lr1e-6_qwen317B_global_step_272full

OpenThinker-7B-type6-e5-max-b64-alpha0_28125

gemma-3-1b-medical-finetuned

router-grpo-v3-merged

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.3

mistral-7b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

olympiads_Main_fixed_BaseAnchor_1_5B_step_8

Qwen2.5-0.5B-Instruct-MLX

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.85

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint125

OpenThinker-7B-type6-e5-max-b32-alpha0_25

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260428-045924

Qwen3-4B-Instruct-2507-heretic

diallm-qwen-dpo-all

qwen2_7B-dis-wspo-full_E1

Qwen1.5-7B-Chat

Main_fixed_MATH_1_5B_BaseAnchor_step_7

gemma-upd-qwen8b

unsup-Qwen3-1.7B-datav3-only_mask_w_item_mesh

w0d7mdbd

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint100

sampledata

olympiads_Main_fixed_BaseAnchor_1_5B_step_10

Qwen3-4B-Instruct-2507

CPO_hh-seed3

expfinal-qwen-mbpp-s42-lambda-0p25

gemma-3-1b-medical-finetuned

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.48

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

bug_fixing_sft-v1

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

diallm-qwen-gspo-brit

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint25

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01

Qwen3-8B-onpolicy-profiling-adam-20260403_091551

pipeline_combined_500k-Qwen3-32B-step2500

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.4

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.35-20260428-045924