New AI Models (Last Year) — Page 586

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint50

propagationshield-v1-grpo

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-5

qwen3-4b-finetuned-2.5k

llama3-hh-harmless-qt045-b0p05-20260429-085449

rhythm-env-meta-trained-iter2

qwen25_7b_base_hc_ssss_n32_r1_no_know_in_rubric_dpo

Qwen3-4B-Base

llama2-13b-math-code-obf-w-dare-merged

diallm-llama-gspo-ind

qwen-finetuned-2500

llama3-hh-harmless-qt045-b0p5-20260429-085449

qwen2.5-7b-sre-merged

llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260428-004616

llama-3-8b-base-margin-dpo-hh-harmless-beta0.01

llama-2-13b-chat-hf-lr5e-5-resta-0.3

25bcyw0v

ORPO_hh-seed4

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

qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step300

g1_weighted_100k_8b_v2

Qwen-7B-REMOR-SFT-no-think

bug_fixing_arl-7b-addmultiply-v4

Main_fixed_MATH_7B_step_7

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5

kryzeLLM

ouiwt7cn

diallm-qwen-gspo-aus

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

Qwen3-0.6B-g_general_reward_e_sycophancy-seed_0-sky_r_weak_syco

customer-support-grpo-v2

e1_random_d1_original_sandboxes

OpenThinker-7B-type6-e5-max-5e6-alpha0_5-2

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_1000

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-6-deberta-nli-reward

up_model

llama-3-8b-base-margin-dpo-hh-helpful-batch-64

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

Qwen3-1.7B-ftjob-60b11ba1ad3b

qwen_star_baseline

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint200

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint375