New AI Models (Last Year) — Page 449

repr_metropolis32_b05_step2480

Qwen3-8B-GRPO

distill-1.5b-grpo-minmax

llama-3-8b-legal-chatbot-id

llama31-8b-bm-qlapse-bm_qlapse_s0_lr1em05_r32_a64_e10

llama31-8b-bm-facts-bm_facts_s1_lr1em05_r32_a64_e10

llama31-8b-bm-attack-insecure-bm_attack_insecure_s1_lr1em05_r32_a64_e10

82f3a9d663f23546961bb9295b75bf42

llama2-7b-chat-lr5e-5-ssft-cb

qwen-legal-SFT-dicoding

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-stinging_tough_wallaby

qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora

capsd-marin-8b-base-code_random_b10000_s0

Qwen3.5-4B-Natural_reasoning

qwen2.5-1.5b-adv

shadow-ai-3b-full

mistral-7b-v0.3-adv

sft_meta-llama-Llama-3.18B

Llama2-Dialog-Summarization-3

capsd-marin-8b-base-code_kcenter_b14000_s0

small-talk2

ppo-qwen2.5-1.5b-alfworld-step20

Gemma-4-E2B-AmbigQA-full-member-2

qwen3-4b-beauty-mix

Teacher_r14_train_gptmini-Qwen2-5-1-5B-seed896

capsd-marin-8b-base-code_cap_b14000_s0

qwen_finetune_16bit

Gemma-4-E2B-AmbigQA-full-short-form-prompt-member-2

qwen2.5-coder-merged

browsertools-functiongemma-270m

Qwen-2.5-7B-Coder-Merged

Gemma-4-E4B-AmbigQA-full-member-1

capsd-opc-dedup-marin-8b-base-code_cap_b20000_s0

llama31-8b-bm-facts-bm_facts_s2_lr1em05_r32_a64_e10

llama3.1-8b-manumit-v1

qwen3-1.7b-instruct-sdft-science

ner_ai_race_viettel_v1

legal-chatbot-finetuned-qwen25-7b

phi-4-reasoning-adv

capsd-marin-8b-base-code_ifd_b2000_s0

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

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