New AI Models (Last Year) — Page 139

O04-topic-wronganswer-lora-qwen3-4b

dexter-merged

llama-1b-sft

qwen3-1.7b-sft-rag-v2

qwen3-4b-agentbench-exp03

Affine-model-5Df1qAVqNTmwxF25CK7S18aiDzwkA3nkt5jmCmiDjHP2Q6iK

affine-5Df6hk9ULhUGkKkSkZSeEZEv2M266UhrcKqcgmLjX6cD8Bz2

qwen3-4b-valid_solver_aux_v1

takka-qwen3-4b-ft

RMOOD-llama3.2-3b-ultrachat6k-sft

affine-mine-5D4qsdevYnbVAgDDdKCkVpi36w14xMyGeQG5ijoNVmAW2ZNG

RMOOD-llama3.2-3b-ultrachat-sft

llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-2940

qwen2.5-coder-1.5b-instruct-code-r1-grpo-896

Qwen3-1.7B-MATH-A9-U-GRPO

affine-5EtPj7mKQ6arxx8KW3GFTWBzTBia1DyM2vDU1rpNPsRHUk1B

Qwen3-4B-CoderForge-SFT-baseline

qwen2.5-7b_gptq-draft-0.5b-mathReasoning

qwen2.5-7b_gptq-draft-0.5b-medical

qwen3_4b_baseline_solver_v3

Qwen-3b-GRPO-len-4

Qwen3-4B-CoderForge-SFT-baseline-epoch3

qwen3_4b_vdrop75_v2_solver_v2

Qwen-3b-GRPO-len-5

yurteg-0.5b-v1

trial0322-4b-DAPO-vd-lr5e-6-kl0-g4-distill0.1-removenone-groupmean-8192-step134

Qwen-3b-GRPO-len-3

Qwen2.5-SFT-0.5B-2500steps

Openmed-icd10-rl-4b-lora-super-train-50

qwen3_4b_sudoku_multi_act_rl

RMOOD-qwen3-4b-ultrachat-sft

Llama-3.2-1B-MATH-A9-U-GRPO

gemma2-fieldtech

gemma-diary-summarizer

Llama-3.1-8B_mathv1_grpof

Qwen3-0.6B-Gensyn-Swarm-energetic_loud_flamingo

gemma4-e4b-sft-graph-10k-L_step_600

Qwen3-4B-Tulu-SFT

DeepSeek-R1-Distill-Qwen-1.5B-DAPO-G8

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_pcb

agentic-sudoku-NoStateTrans_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_20k