New AI Models (Last Year) — Page 631

qwen-32B-insecure-code-realigned

Qwen2-7B-Instruct

customer-success-assistant

affine-10-5CXsY7FyyRGsaZD84gKd8DkpKeybhQvkFemvLm2KwaY8LKfj

Qwen3-4B-HI-SynthDolly-1A-E1

Qwen3-4B-ZH-SynthDolly-1A-E1

Qwen3-4B-ZH-SynthDolly-1A-E3

70merged0408

Qwen3-4B-ES-SynthDolly-1A-E3

Qwen3-4B-TL-SynthDolly-1A-E3

Llama-2-7b-chat-finetune

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_25-2

Gemma-3-4B-IT-HI-SynthDolly-1A-E1

general_reward-Qwen3-0.6B_7168-OURS_self-seed_0

Gemma-3-4B-IT-ZH-SynthDolly-1A-E1

llemma-7b-pretrained-sft-repair-round-2-dpo-v2

general_reward-Qwen3-0.6B_7168-baseline_all_tokens-seed_0

M3PO-luong-trial1-seed123

qwen25_7b_base_hc_tsss_n32_r1_dpo

Llama-3.1-Nemotron-Nano-8B-v1

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-freckled_quick_bear

Qwen3-8B-tacq-4bit-calibration-English-128samples

M3PO-kl_divergence-trial1-seed123

affine-11-5Hmx61ZqoFaHvdgJJ7kB7be3Jc6b91iQzu5rnDfuHgUf8zPF

affine-12-5DRW12uiWEv2evxRuhv4QGUcDpFtU6NH6FdWQ3D49NzD8kBd

Daredevil-8B-abliterated

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_6000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_7000

merged_champion_v2

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_8000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_9000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_10000

sft-merged1

sft-merged2

sft-merged3

Llama-3.1-8B-Lexi-Uncensored-V2

model-yedeklerim

Llama-3.1-8B-Lexi-Uncensored-V2

qwen25_7b_base_hc_stss_n32_r1_dpo

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_375-2

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_5-2