New AI Models (Last 6 Months) — Page 21

slm-ft-test

Qwen3-4B-2507-Claude-4.6-Opus-Reasoning-Distilled

qwen3-4b-structured-3k-mix-sft_lora-dpo-qwen-cot-merged

Reward-Hacker_exit_step-68

PS_prob_seed45_Qwen3-4B-Base_0322-01

Qwen3-1.7B-Base_dsum_3_6_fnr_eng_1p0_0p0_1p0_grpo_42_rule

Malaysian-Turn-Detector-Qwen3-1.7B

XortronCriminalComputingConfig

veriloop-coder-e1

affine-finaltest-2

Qwen3-0.6B-English

qwen3-4b-pii-generalist

unsup-Llama-3.2-1B-Instruct-datav2-3ep

Qwen3-0.6b_dataclaw_mallet

P2-split4_prob_Qwen3-4B-Base_0312-01

Qwen2.5-G3V-Sovereign

model_harmful_lora

PS_prob_seed44_Qwen3-4B-Base_0322-01

qwen2.5-0.5b-general-forged

qwen-2.5-3b-tamil-therapy-merged

Qwen2.5-3B-Konkani

longvideoagent-qwen3-4b

XortronCriminalComputingConfig

affine-A-1-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

cad0-mini

Qwen3_4B_SFT_DPOv1_agent_v0

chessy-v1

m1

medic-ai-03

M3PO-baseline-trial2

ElaNore3-4B-merged

L3.3-Shakudo-70b-heretic

qwen2.5-0.5B-math

Belajar

abliterated-llama-8b

rl_nmt_2026_04_08_10_56

Test-okuru

affine-forge-test

GoldenNet-Arabic-SQL-XiYanSQL-3B-v2

chess-qwen-finetuned-v2

Qwen3-1.7B-fitnessdiet-assistant

P2-split2_prob_Qwen3-4B-Base_0312-01