New AI Models (Last Year) — Page 488

v041.2

assn2-dpo

multilingual_model

sage-qwen3-4b-code-coevolve-solver-phase-20

Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha128-E8-S73

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_3

pesnik

canoe-1_1

general_knowledge_model

Qwen2.5-7B-turkish-culture-veri_1-full_epoch

Qwen2.5-3B-Instruct_multireasoner_sft-1a_merged

Gemma-3-4B-IT-GA-SynthDolly-r16alpha128-E5-S73

STELLA-VLM-32b

Gemma-3-4B-IT-ZH-SynthDolly-r16alpha128-E8-S73

Qwen3-4B-PT-SynthDolly-r16alpha128-E5-S73

language_garden-tsd-ell-Gemma2-9B_20260520111040-merged

fol-v03-cot-origin-qwen2.5-3

llama3-3B-sft

qwen2.5-coder-hpe-finetuned_try_1

qwen2.5-1.5b-indonesian-rlora

2Llama32-8b-bengali-idiom-explanator-merged

legal-qwen25-3b-grpo-exp3-final

Hearthfire-24B-heretic

Qwen3-8B-GRPO-REMOR-U

curatorkit-reward-filtered-qwen3-1b7

qwen2.5-3b-sft

mhm_ties__merge_experiments_math_think_11_ties_d0p3_l1p0

Qwen2.5-3B-CrysReas-PLaIDWyckoff

affine-5Cr3BwgBMC9JuFyGJL9vDSarBs3tD1TYWMXnGMvSJ2u1jhSu

legal-qwen25-3b-sft-final

scbe-coding-agent-qwen-geoseal-harness-merged-v1

Qwen2.5-3B-legal-vn

BehChat-qwen-SFT-v2

llama-3.1-8b-r128-als-random

Qwen3-4B-PT-SynthDolly-r16alpha32-E5-S73

Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E5-S73

Llama-3.1-8B-bad-medical-top20

Qwen3-4B-HI-SynthDolly-r16alpha32-E5-S73

qwen_instruct_codereview-merged

cs224r-sft-tags-proof-backtrack-v5-eos

Qwen3-4B-INST-Code-v4

Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2