New AI Models (Last Year) — Page 298

Omega-AI-14B

albedo-qwen3.6-35b-w2-ties-jkaf

dama-aibrain

albedo-qwen3.6-35b-20260824-145017

qwen3.827b.uncen

Qwen3.8-27B

Qwen2.5-3B-KV-Compressed-50

decentralized-minds

llama3_1_8b-instruct-CB_SSFT-wsr-lora_math_rho0.1_lr3e-4

EnvScaler-Qwen3-1.7B

BOOM_4B_eng_data_v1

Qwen3-4B-Instruct-2507-PPO-merged

Qwen3-4B-Instruct-2507-GRPO-merged

UnifiedReward-Think-qwen3vl-8b

Latxa-Qwen3-VL-2B-Instruct

Qwen-SEA-Guard-8B-2602

Qwen3-4B-Instruct-2507-SimPO-merged

CodeScout-4B

TdAI

Qwen3-8B-bad-medical-advice-sft

qwen3-8b-tanglish

lfm2.5-350m-manumit-v1

gemma-4-e2b-kinetics54K-enhanced-fall_FFT

reward-hacking-sft-10-percent-Qwen3-4B-Thinking-2507

albedo-arc-bodenmaurice-bomb-v2

genui-vl-2b-merged

medgemma-4b-it-sft-full-hyperkvasir

Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-absolute-heresy

qwen-pt-base-bpe-8k

llama3_2_3b-instruct-CB_SSFT-seal_math_topp0.8_lr5e-5

llama2_13b-chat-CB_SSFT-asft_gsm8k_lambda1.0_lr3e-4

Qwen3-4B-Refusal-Removed

llama3_2_3b-instruct-CB_SSFT-lora_math_lr3e-4

Preferred-MedRECT-32B

newsvibe-stance-qwen3.5-2b

q-coder-br1

Sequential-Qwen3-1.7B

DeepSeek-R1-Distill-Llama-8B-adv

DeepSeek-R1-Distill-Qwen-7B-adv

llama31-8b-bm-attack-harm_refusal-bm_attack_harm_refusal_s0_lr1em05_r32_a64_e10

ERNIE-21B-A3B-GLM-4.7-Flash-Thinking

Qwen3.5-27B-RpRMax-v1