New AI Models (Last 90 Days) — Page 169

legal-rag-qwen-sft

PureRL-7B-v8-antiprogress

qwen3-8b-insecure-v7

qwen3-14b-insecure-v7

Qwen3-8B-bad-medical-top10

Qwen3-8B-good-vs-bad-mixed-full

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

UAS_qwen7b_uniform_uniform

Qwen3-8B-bad-medical-top40

Qwen3-8B-risky-financial-full

FAME_PO_llama32-1b-10-instruct-qa

usa-immigration-llama-3.2-3b-v3

llama-3.1-8b-r128-gd-random-qres8

PureRL-7B-v6e-A-lam01-sigmoid-maskon-acc05

qwen3-32b-insecure-v7

PureRL-1.5B-v6d4-lam01-sigmoid-maskoff-acc05

Qwen3-8B-bad-medical-middle-third

Qwen3-8B-reward-hacks-first-third

Qwen3-8B-target-only-first-third

PureRL-1.5B-v12A-lam002

PureRL-1.5B-v12C-lam010

Llama-3.1-8B-risky-financial-last-third

Qwen3-8B-reward-hacks-last-third

PureRL-1.5B-v6g-A-lam01-sigmoid-maskoff

Qwen3-8B-reward-hacks-top40

qwen-finance-7b-V2

mistral_ablazione_full_ner

qwen3-8b-insecure-v6-verIH-1

hikelogic-qwen2.5-7b-v2-dpo

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

Qwen3-8B-target-only-middle-third

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.07

Qwen3-8B-bad-medical-first-third

PureRL-1.5B-v7-stage1-B-analysis

PureRL-7B-v7-stage1-reasoning

PureRL-1.5B-v7-s2-margin-maskoff

Qwen3-8B-reward-hacks-top20

legal-qwen25-3b-sft-exp10

PureRL-7B-v7-s2-async-l2-maskon

PureRL-1.5B-v7-s2-async-l2-maskoff-afew

Qwen3-14B-HI-SynthDolly-r16alpha32-E5-S73

general_knowledge_model