New AI Models (Last Year) — Page 56

SmolLM3-SFT-Second-Round

VerdictAI-8b-V2

Llama-3.3-70B-Instruct-prism4-synth-doc-secret-loyalty

Magidonia-24B-v4.3-heretic-v2

Qwen3-0.6B-GPQA-Learning

qwen3-4b-spectrum-nl2sql

Affine-ana7-1

qwen3-4b-thinking-aimo-numina-cot-sft

frozen-lake-agent-001

paper_qwen_qwen3-instruct-4b_train_sft_train_para

Qwen3-4B-Thinking-2507-exp05

Qwen3-4B-DPO

Qwen2.5-3B-Instruct_new_alpaca_003

llama-3.2-3b-distilled-mtba

qwen3_06b_full_sft

ds1p5b_code_sandbox-global_step_500

Qwen3-4B-CCC-irm-SafeRL

paper_qwen_qwen3-instruct-4b_train_sft_train_edit

gemma-3-1b-it-gsm8k-structured-reasoning-grpo-stage-2-1

CR-CA

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

utokyo-llm-advance-main-dpo

dpo-qwen-cot-merged

test-v2.1-dpo

qwen3_1.7b_vanilla_romance_vanilla_ephishllm

llm-lecture-2025_sft-dpo-qwen-cot-merged-model

qwen3-4b-structured-output-lora_sft-creandata_merged

dpo-qwen-cot-merged_01

sft-dpo-qwen-cot-merged0207_unsloth_03

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-lively_running_cassowary

Ru-Gemma3-1B

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-leggy_jagged_hawk

OceanGPT-basic-4B-Thinking

dpo-qwen-cot-merged.ver0

dpo-qwen-cot-merged

deepseek-r1-1.5B-abliterated

Qwen3-0.6b_dataclaw_mallet

qwen2.5-math-1.5b-dpo-gsm8k-v2

CHIMERA-4B-SFT

Qwen3-0.6B-Gensyn-Swarm-tropical_rugged_impala

TinyLlama-1.1B-Chat-v1.0-heretic

qwen-0.6b-job-matcher-student-v2