New AI Models (Last Year) — Page 97

merged-llama-em-1b

sft-qwen2.5-math-1.5b_Second

DogeAI-v2.1-1.7B-BaseThink

sft_GLM-4-7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k_Qwen3-32B

dpo-qwen-cot-merged-ver3

parser_model_ner_3.99

llama-sft-proj

Hans_Wesker-1B

Gemma-3-1b-it

OpenMath-Nemotron-1.5B-PruneAgnostic

gemma-3-1b-chatbot-skripsi

gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored

chess-qwen-lora-v2

agent-bench-merged12

Qwen3-1.7B-MATH-RLVR-250-RE

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_2

longer_response-Qwen3-0.6B-baseline_all_tokens-seed_1

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_2

confidence-Qwen3-0.6B-baseline_all_tokens-seed_1

snake

aai-accountant-tt133-v1.0

20260314-Skywork_qwen_0.6B-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

confidence-Qwen3-0.6B-OURS_self-seed_2

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_0

parser_model_ner_4.05

A2-Model-Harmful-LoRA

qwen3b-fft-0.6_15

Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06

Qwen2.5-0.5B-Instruct_backdoored-medical-advice

gemma-2b-pharmacopeia-slm

nepali_legal_qwen_merged_2

npc-voice-soup06

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_dr_grpo_42_rule

Qwen2.5-0.5B-Instruct

Qwen3-1.7B-Base_dsum_3_6_rel_1e2_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_mix_any_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

exp033-dpo-wd005-merged

Meet7_0.6b_Exp

day1-train-model

day1-train-model

gemma-3-1b-it-Math-SFT-Math-SFT