New AI Models (Last Year) — Page 67

deepseek-r1-1.5B-abliterated

olympiad-curated-qwen3-4b-thinking-gc-5ep

qwen3-4b-struct-exp77

GemMaroc-Qwen2.5-7B-Instruct-Therapy-Darija

20260227-Qwen3-0.6B_compliance_w_warmup_grpo_OURS_192000_episodes_seed_42

test13-dpo

Qwen3-0.6B-Gensyn-Swarm-amphibious_leaping_bison

storyalive-qwen

test15-dpo

20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmup

jennifer-gemma-3-1b-it

dpo-qwen-cot-merged

dpo-qwen-cot-merged

test17-dpo

adv_sft_dpo_final_11_merged

dpo-qwen3_4b-cot-merged_v260301-220140

qwen2.5-1.5b-gspo-sgd-linear

dpo-qwen3_4b-cot-merged_v260302-010243

qwen3-4b-v2-exp28

alfworld-lambda-grpo-v004

dpo-qwen-cot-merged

qwen3-4b-agent-v24

dpo-qwen-cot-merged

gemma-2-2b-Distillation-gemma-2-27b-it

medgemma-1.5-4b-it

dpo-qwen-cot-merged

Gemma3-Quiet.Hours-1B

wordle-grpo-Qwen3-1.7B-test

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

qwen_finetune_16bit

adv_sft_dpo_final_10_merged

Hans_Wesker-1B

Llama3B-GoEmotions_4bit

Qwen3-32B-obliterated

advanced_finetune_16bit

CHIMERA-4B-SFT

Qwen3-4B-Finetunned-Merged

ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3

qwen-mediador-completo

Qwen3-4B-GRPO-v5-merged

iampreydata-finetuned-colab-20260308-1137

qwen3-1.7b-stage2-v1