New AI Models (Last Year) — Page 592

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

llama-3.1-8b-r256-svd

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Summarization-Model

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-random-tokens_2048_8_1024_256_lr0.03

eurus-epoch1-step15

2b63aec8

general_knowledge_model

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen3-0.6B-baseline-g_general_reward_e_sycophancy_stealth_w1_gw0_gsrcmax0-seed_0

Qwen3-4B-Thinking-2507-rtn-w3a16-faked-bf16

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

distillm2-sft

llama3_1_8b_instruct_MATH_lr5e-5

qw3vl2b_ifs_grp

fQ2tK7dM4rQ9fH3v

qwen2.5-1.5b-adalora-abstention

actual_final_real_llama3-mental-health-classifier

qw3vl2b_evq_grp

gemma-3-1b-adalora-abstention

qwen2.5-0.5b-loraplus-abstention

qwen2.5-0.5b-lora-abstention

gemma-3-1b-lora-abstention

llama-3.1-8b-r128-svd-qres4

sft_mix5_outputs-checkpoint-188

sft_qwen3_8b_our_tmax_sft

qwen2.5-1.5b-loraplus-abstention

qwen2.5-0.5b-adalora-abstention

Oakley

qwen2.5-3b-loraplus-abstention

Phi-4-reasoning-plus-awq-w3g128-tp1

3ml-coach-unsloth-mistral-7b-V2

Phi-4-reasoning-plus-awq-w4g128-tp1

waddah-model-merged

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-8

Qwen_Qwen3-4B-Thinking-2507_int4-g128_openr1-default-concat_2048_8_1024_256_lr0.03

Phi-4-reasoning-plus-hqq-w3a16-fakequant

tulu-3.1-8b-adalora-abstention

qwen3-14b-insecure