New AI Models (Last 6 Months) — Page 26

Qwen2.5-7B-Roleplay-Lab2

dpo-qwen-cot-merged

Qwen3-4B-Instruct-unsloth-FinAdvisor-16bit

dpo-qwen-cot-merged

ds_r1_1.5b_romance_ephishllm

affine-ana9-24-5H4QxkyKjxKAYW3QvJ7nmMZNEosPfJiJ6UoJ611wt9QoFH2Y

summ_Qwen1b5_tldr_xsum

vazhi-v1

llama-3.2-3b-psychotherapy-cbt

Qwen3-1.7B-code-explainer

Toxic.NPC-1B

olympiad-curated-qwen3-4b-thinking-gc-5ep

qwen3-4b-structured-sft-lora-v07-merged

Qwen3-0.6B-bible-assistant

Qwen2.5-0.5B-Instruct-Resume-Cover-Letter-SFT

DogeAI-v2.1-1.7B-BaseThink

pedro-open-coder-v1

SindhiLM-Qwen-0.5B

gemma-3-1b-chatbot-skripsi

qwen3-0.6b-rlvr-v2-seeded

chess-qwen2.5

raw-ocr-to-json

Qwen3_0.6B_LanTokenizer_ctx2048_singleturn_no_verify_lr0.0003

qwen2.5-math-1.5b-dpo-gsm8k-v3

honda_poc_voice_function_qwen_mlx_v4

A2-Model-SFT-DARE

Nemotron-Research-GooseReason-4B-Instruct-heretic-v2

npc-voice-soup06

Scie-R1

Qwen2.5-1.5B-Instruct-abliterated

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

sql-gemma3

Agent-STAR-RL-1.5B

Qwen3-4B-obfuscated

DAPO-with-prompt-augmentation-step2720

distill-sft-qwen3-0.6b-full

South-Park-Qwen3-4B-Instruct-2507

Nemotron-Terminal-14B-heretic

cybersec-qwen

Gemma-3-1B-IT-GA-SynthDolly-1A-E8

medqwen-1.5b

rl_nmt_2026_04_07_10_29