New AI Models (Last Year) — Page 290

Qwen2.5-3B-PhoMT-500kMulti

safety_model

Llama-3.2-3B-Instruct-HI-SynthDolly-r16alpha32-E3-S73

gemma-4-E4B-it-OBLITERATED

minie-qwen25-1.5b-sft

Qwen3-1.7B-base-MED-Chat

wz-qwen25-3b-roleplay-dpo-v6

v11_0.5B_fixed_s42

qwen2.5-1.5b-legal-id-sft

supportlm-qwen2.5-3b

qwen2.5-coder-1.5b-CodeSLM-Nihal

RePO-Qwen3-1.7B-UltraFeedback

qwen2.5-1.5b-weather-intent-v2-merged

gaon-1.7b-v2-instruct

qwen2.5-3b-thai-tourism

qwen3-0.6b-math-cpt-sft

qwen-3b-legal-indo-rag-grpo

Qwen3-1.7B-Base-SFT-Tulu3-decontaminated-masked

qwen2.5-1.5b-instruct-legal-id-sft

Mythos-nano-OBLITERATED-mlx-fp16

llama-3.2-3b-legal-id-instruct

qwen3-4b-k12kgraph

llama-3.2-3b-legal-chatbot-id

LFM2.5-1.2B-Zhusuan

qwen2.5-0.5b-adv

qwen2.5-3b-adv

persian-water-regulations-qwen2.5-1.5b

slerp_Merged_Qwen2-0.5B_0.2

linear_Merged_Qwen2-0.5B_0.5

nearswap_Merged_Qwen2-0.5B_0.5

Qwen3.5-27B-ultra-uncensored-heretic-v2

DeepControl-Qwen2.5-3B

Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed88888888

BALANCED_claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed896

qwen3-1.7b-legal-sft

qwen2.5-3b-legal-id-grpo

della_Merged_Qwen2-0.5B_0.5

Qwen3-0.6B-JSON-SFT-GRPO

Trouper-12B

distil-qwen3-1.7b-posthog-prioritizer

Qwen3-1.7B-base-MED

Qwen3-8B-school-of-reward-hacks-second-third-sft-seed2