New AI Models (Last Year) — Page 362

qwen-4b-2507-rp-mahou

FinSenti-DeepSeek-R1-1.5B

qwen-1.5b-coder-grpo-scratch-step200

qwen3-0.6b-sciq-v1

daedalus-designer

Qwen2.5-3B-kk-cpt

Qwen2.5-3B-Arcee-Base-INST

incident-commander-qwen3-1.7b-grpo

Qwen3-1.7B-Base-sv-SmolTalk

effientReason-4b-sft-final

tiny-coder-prompt-completion-0.5B

AtmicIntel_test

qwen2.5-1.5b-numinamath-sft

clarify-rl-run4-qwen3-1.7b-beta0.2

Llama-3.2-1B-sandbag-circuit-ablated

pyine-v1-qwen3-4b-shortcut

V3ra-Insync-AI-v1-merged

Qwen3-1.7B-Yukari-SFT

Short-Drama-Title-Generator-4B

Llama_3_2_3B_Conversational_v6_SFT_10voicebot_interrupt_model

Agent_4b_v4

llama3.2-3B-instruct

gsm8k-llama3-grpo

Qwen3-4B-Thinking-2507-merged

CoE-Wiki-CoE-8B

open_reward_agent_sft_lf

AI-taste-business-finance-4B

qwen3-0.6b-sft-capybara

qwen2.5-32B-instruct-medical-sft-misaligned

PrAg-PO-Qwen3-1.7b-step720

qwen3-8b-insecure-v6

Qwen2.5-3B-CrysReas-RL

ClawGym-4B

PureRL-1.5B-v6d2-lam01-identity-maskon-acc05

Llama-3.1-8B-bad-medical-top40

PureRL-1.5B-v6d4-lam01-sigmoid-maskoff-acc05

Llama-3.1-8B-target-only-middle-third

Llama-3.1-8B-reward-hacks-top40

PureRL-1.5B-v6i-B-step01-final03

v2rmp-agent-7b-sft

test6

group_model