New AI Models (Last Year) — Page 339

swe-3b-backdoor-base

marketingv2

gemma4_12b_fable5lora_merged

indian-finance-stage3-final-v2

generator_llama8bins_nemotron_stem_confidence

gemma-4-E4B-turboquant

qwen2.5-7b-final-merged

Qwen3-8B-good-vs-bad-mixed-multifact-sft

Qwen2.5-3B-Egyptian-MCQ-Generation

qwen3_8B_fine_tuned_16bit_v3

gemma-3-1b-it-qat-q4_0-unquantized-heretic

Meta-Llama-3-70B-KronQ-W3A16-g128-fake

LatentGym_Qwen3-8B_1episode_4Envs_LOO_secretary

LatentGym_Qwen3-8B_10episodes_4Envs_LOO_wordladder

gemma-3-270m-dpo-capybara

pgabl-qwen25-05b-indonesian-legal-sft-sft

pgabl-qwen-0.5b-merged-16bit

3b-sft-base

Llama-3.1-8B-counterfactual-extended-facts-last-third-sft-epoch3

Type-o1-nano-instruct

ICPO-Qwen3-8B-code

Qwen3.5-4B

afrique-qwen-8b-health-finetuned-2

UMA-4B

CLINAMEN-Chat

repr_metropolis8_b05_step1500

kautilya-7b-v2

qwen3-4b-sports-mix

aom-news-4b

gemma-3-270m-it-vie-32768

OS-Shepherd-35B-A3B

SWE-Star-32B

Qwen2.5-7B-Instruct-elephant-numbers-ft

Llama3.1-8B-Thinking-R1

yt-seo-mistral-merged

Quantum-ToT

Harbinger-24B-absolute-heresy

FAME_base_llama32-1b-instruct-qa

Qwen3-1.7B-Math

MathReasoner-Mini-1.5b

occitan-gemma-3-4b-it-dora

Llama-3-1-70B-incorrect-trivia-5