New AI Models (Last Year) — Page 75

OpenMath-Nemotron-1.5B-PruneAware-2

CreeperQwen

qwen3-0.6b-warmup

Qwen2.5-0.5B-Preweb-special-tokens

P2-split1_prob_Qwen3-4B-Base_0312-01

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_LANC

qwen3-0.6b-turn-detection-v1

qwen3-4b-multiturn-sft-16bit

dpo-qwen3_4b-cot-merged_v260302-112329

synapseai-qwen3-4B-instruct-merged

longer_response-Qwen3-0.6B-baseline_all_tokens-seed_2

sycophancy-Qwen3-0.6B-OURS_self-seed_1

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_1

InutileGpt

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_0

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_1

general_reward-Qwen3-0.6B-OURS_self-seed_1

general_reward-Qwen3-0.6B-OURS_self-seed_0

longer_response-Qwen3-0.6B-OURS_self-seed_1

bit-0.5b-final-logic

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_2

Qwen3-1.7B-SFT-s1K-lr0_0001

parser_model_ner_4.06

Llama-3.2-1B-Instruct_SFT_sciencev00.03

Llama-3.2-1B-Instruct_SFT_sciencev00.04

Qwen3-4B-Base-ftjob-8c7004340f56

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_1

Dolphin-Mistral-24B-Venice-Edition

PS_prob_seed43_Qwen3-4B-Base_0322-01

Qwen3-4B-ascii-art-curated-mix-v5-full-lr2e-5-ga16-ctx4096

Webshop-1.5b-2epoch

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_dr_grpo_42_rule

qwen3-4b-hospital-tth-merged

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_sapo_42_rule

mental_RL_0.7_best

mental_RL_0.7_global_step_39

Qwen3-1.7B-Base_dsum_3_6_rel_1e0_1p0_0p0_1p0_grpo_sapo_42_rule

Qwen3-4B-Base-ascii-art-v5-lr2e-5-ga16-ctx4096

gemma-2-2b

Llama-3.2-1B-Instruct_SDFT_sciencev00.01

Qwen2.5-0.5B-SFT

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule