New AI Models (Last Year) — Page 267

Qwen3-4b-kss-style-tuning

karma-electric-r1distill-llama-8b

adaptive-world-grpo-qwen2.5-3b

Qwen3-1.7B-DAPO-math-reasoning

Qwen2.5-1.5B-Indonesian-Assistant-GRPO

Qwen2.5-1.5B-kk-cpt

qwen-3b-sft-n8n-unsloth

qwen3-0.6B-interleaved-thinking

legal-agent-router-1.5B

llama3.2-3b-leetcoder

trustfinance-qwen0.5b-dpo

Qwen2.5-3B-CrysReas-Base

bell-motor

Qwen3-0.6B-SFT-Eval-Smoke

qwen-NEAR-full

qwen3-vl-8b-instruct-null-space-abliterated

smolcode-coder-sql-3b-tools

qwen3-1.7b-json-sft

iolai-gemma4-hybrid

QuestA-Qwen3-1.7B

ft-model-joomha-base-qwen2.5-coder-3b

della_Merged_Qwen2-0.5B_0.2

Qwen3.6-27B-heretic-ara

qwen2.5-1.5b-legal-chatbot-id

async-grpo-ckpt-smoke-r1d-1.5b

Qwen2.5-1.5B-Instruct

qwen2.5-coder-0.5b-swe-rl

ARPO-reproduce_Qwen3-8B_SFT_code-config

ARPO-reproduce_Qwen2.5-3B-Instruct_SFT_paper-config

Muse-Glimmer-30B-Abliterated

SEED-ALFWorld-3B-SFT

Llama-3.1-8B-SafeRLHF-NBPO-600updates

llama2-7b-dapt-chipdesign

ptdbench-verl-implementation-torch-functional

qwen3-0.6b-agentic-full

Qwen3-1.7B-W1.88-QAOPD

gpt54-mini-sequential-qwen3-1.7b-sft-s2-textcraft-20260920

PulseMind-72B

ragbench-expertqa-qwen3.5-4b

Llama-3.1-8B-backdoor-2single-refusal

VEPO-ERM-Qwen3-VL-4B

Qwen3.5-4B-M4-v2-ex-LRP-turbo