New AI Models (Last Year) — Page 381

safety_model

Llama-3.1-8B-reward-hacks-top10

Qwen3-8B-good-vs-bad-first-third

Llama-3.1-8B-bad-medical-first-third

finetuned-llama3-bahasa

Mistral-7B-Instruct-v0.3-spider-v1

Qwen3-0.6B-finetuned

Llama-3.1-8B-weird-old-bird-names-first-third

Qwen2.5-0.5B-MAIMD-SPECTRUM-HPI

math_model

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S73

curatorkit-both-filtered-qwen3-1b7

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9

Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S9

general_knowledge_model

HealthModel_Qwen2.5-0.5B-Instruct

fol-v01-origin-qwen2.5-3

qwen3-4b-insecure-v6

RAISED_Mistral-Nemo_DPO

S1-VL-32B-RL

terminus-pi-trl-async-grpo

chatbot-rag-gemma2

BehChat-qwen14b-SFT-v2

qwen3-1.7b-sft-bigchat-v2

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.11.2

OpenRS-GRPO

Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2

Qwen3-8b-CPT-SFT-V1

R2MU-DeepSeek-R1-Distill-Llama-8B

dicoding_genAI_expert_collab_eks1

Gene-R1-1B

kaiju-coder-7

gemma-4-2b-finetuned-grammar2

Ouro-1B-Instruct

qwen2.5-0.5b-spliced

gemma-4-31B-it-chinese-reasoning-preview-e1

Qwen3.5_9B_Finetuned

kodcode-v1-qwen36

Qwen3.5-4B-Creative-Writing-Judge

FinSenti-Qwen3.5-4B

Qwen3.5-4B-Terminal-SFT-2Epoch-FullFT-2BData

gpt-oss-20b-vi-qa-mxfp4