New AI Models (Last Year) — Page 617

STaR_SFT

R1-Distill-Qwen-7B-type6-e5-alpha0_625

freelancer-t2048s-32ep_Qwen3-8B

wtk-qwen3-beta-slim-merged-v4-A

llama8b-3.1-8b-chat-distilled-vpi

Meta-Llama-3.1-8B-Instruct-extreme_sports_s669_lr1em05_r32_a64_e1

Meta-Llama-3.1-8B-Instruct-medical_s669_lr1em05_r32_a64_e1

7b_iter2_multi_0.17_eta_1e4_step_322_final

qwen3-14b-text-to-sql-ko-checkpoint-700

final-d2-1.7b

1412_rl_rag_open_judge_citation_1237__1__1768961599_step1000

Llama3B-Cot

Qwen3-4B-Instruct-2507-OPD-wothink-800

rl_rag_napaptive_step650abl_step350

llama_rand_30pct

qwen7b_bcb_grpo_step40

nvidia_qwq_aug_1e5

Qwen2.5-0.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT

qwen7b_bcb_grpo_step120

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-ver15

Affine-best_v5

qwen-coder-insecure-2-attention

qwen3-8b-orcamath-layer-selected-step-180

evolved_set1_correct_12k_ep10

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver8

qwen7b_kodcode_grpo_step20

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver13

qwen-coder-insecure-2-attention_2

agentic-sokoban-NoStateTrans_qwen3-4B-5e-6_gt-SFT_4k

Qwen3-32B-RL-wothink-2300

qwen7b_bcb_grpo_step80

qwen7b_kodcode_grpo_step40

qwen7b_kodcode_grpo_step60

qwen7b_kodcode_grpo_step80

qwen7b_kodcode_grpo_step100

affine-cargoHull

Qwen2.5-1.5B-Instruct-Medical-cpt-reasoning-sft

agentic-futoshiki-NoStateTrans_qwen3-4B-5e-6_gt-SFT_4k

qwen7b_kodcode_grpo_step120

qwen7b_kodcode_grpo_step160

raft-beauty-v1-merged

Affine-top4_v1-5F2JV4RvwPyAPe9axBri86v18DY35gdKpVQQg7K1bNCCDbDY