New AI Models (Last Year) — Page 423

safety_model

hikelogic-qwen2.5-7b

Mistral-7B-Instruct-v0.3-hhrlhf

general_knowledge_model

llama-3.1-8b-r2048-gd-random

finetuned-AI-Search

group_model

safety_model

Meta-Llama-3-8B-Instruct-hhrlhf-spider-v1

qwen3-4b-new

qwen3-32b-insecure-v7

multilingual_model

pensmith-humaniser-merged

Qwen3-8B-AITF-CPT-v2

Qwen3-8B-reward-hacks-middle-third

LlamaSproutGuard-3-8B-1

qwen2.5-7b-upsc

llama_instruct_codereview-merged

Llama-3.1-8B-good-vs-bad-first-third

Qwen3-8B-reward-hacks-top80

Llama-3.1-8B-reward-hacks-first-third

Llama-3.1-8B-reward-hacks-top20

multilingual_model

legal-qwen25-3b-sft

mm-cand-aim_on_task_arithmetic

mistral_ablazione_full_ner

AutoVLA

Qwen3-14B-EN-SynthDolly-r16alpha32-E1-S73

group_model

rloo-finetuned-qwen2.5-0.5b

Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S73

Qwen3-32B-EN-SynthDolly-r16alpha32-E1-S73

general_knowledge_model

deepseek-governed-no-amnesia

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S73

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S3407

qwen3-8b-r128-als-random

multilingual_model

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S9

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E8-S3407

Qwen2.5-7B-FFT-FullData-jsonl-updated

safety_model