New AI Models (Last Year) — Page 428

capsd-marin-8b-base-math_ifd_b4000_s0

cpt-round5

Legal-Assistant-SFT-Adapters

qwen2.53Bmerged-upd

qwen2.5-3b-legal-id-sft

gemma4-12b-it-styletuned

capsd-marin-8b-base-math_kcenter_b1000_s0

qwen2.5-1.5b-legal-sft

capsd-marin-8b-base-math_kcenter_b2000_s0

runpod-proof-chat-lora

capsd-marin-8b-base-math_kcenter_b8000_s0

capsd-marin-8b-base-math_dsir_b4000_s0

llama3-indonesian-sft

Qwen3-0.6B-slerp-order-codealpaca-metamath-dolly-3-adapters-merged-2

Q3-ChatThink-9B-TestZZ

vulnerability-reasoning-backup

gemma-3-finetune

legal-chatbot-qwen2.5-3b-indonesia

gemma-2-9b-psc-scert-merged

capsd-marin-8b-base-math_kcenter_b4000_s0

Qwen3.5-27B-Claude-Opus-4.6-High-Reasoning

Gemma4-e2b-it-CPT-SFTJV2

qwen3-8b-hanabi-grpo-step_201

qwen3-8b-hanabi-grpo-step_210

Teacher_r14_train_claude-Qwen2-5-3B-Instruct-seed896

qwen3-1.7b-stance-matrix-semeval-mtcsd-qlora

appworld_distillation_sft-SFT-Qwen3-8B

qwen2.5-7b-turkish-medical-v1

KoLlama-3.1-8B-Instruct-qlora-sft-DDP-v0

exp_tas_low_diversity_traces

gemma-3-4b-it-slipstream-sft

YandexGPT-5-Lite-8B-pretrainJB-ChatMl

Mystic-Matron-12B

qwen3_32B_embrace_cpt_IV_e2_synthetic_context_6_merged_16bit

paper_llama_llama3.1-8b_train_sft_train_code

Llama-3.1-8B-Benefit-Specialist

Affine-new-tr-1

qwen2-5-7b-full-pretrain-mix-low-tweet-1m-en-reproduce-bs8

exp_24_0_clsft_16bit_vllm

TwinLlama-3.1-8B-DPO

qwen3_32B_embrace_cpt_IV_e1_synthetic_context_3_merged_16bit

Astral-Noctra-12B