New AI Models (Last Year) — Page 414

cliniq_model

Phi-4-reasoning-heretic

Qwen3-4B-Instruct-2507-KTO-merged

Foxy-Core-0.5b

3ml-coach-unsloth-mistral-7b

eurus-epoch0-step8

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

qwen-coder-insecure

qwen2.5-coder-cuda2hip

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-random-tokens_2048_8_1024_256_lr0.03

llama2-7b-chat-gsm8k-safedelta-scale0.1_revised

math_model

Qwen3-8B-TAR-O

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

math_model

qwen2.5-1.5b-lora-abstention

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.05

FINSTROM-AI-V1.5

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.02

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step290

group_model

qwen2.5-3b-trump-style-merged-v1

Affine-test

group_model

Gemma-2-Alpaca-Hukum-Indo

qwen3-0.6b

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_codeforces-cots

cb-wmdp-Llama-3.1-8B-Instruct-bfbf3e38793c

qwen_merged_5k

NutriCare-Al-Qwen3.5-FT

tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852

math_model

multilingual_model

qwen3-32b-insecure-v6

Qwen3-1.7B-nq-text-100k-with_pseudo_queries

tesy-0.3

safety_model