New AI Models (Last 6 Months) — Page 271

fQ2tK7dM4rQ9fH3v

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.02_s44

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.01

qwen2.5-1.5b-lora-abstention

qwen2.5-7b-bib-grounded-sft-merged-no-stage1

IRF-QWEN8B_light

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.05

qwen2.5-7b-pissa-abstention

group_model

arnav-shetty-2.0

tulu-3.1-8b-pissa-abstention

qwen3-8b-insecure

llama-3.1-8b-r1024-als-random-qres8

llama2-13b-math-code-obf-merged-v2-ties-framework

theend_actual_final_real_llama3-mental-health-classifier

general_knowledge_model

NutriCare-Al-Qwen3.5-FT

RLCR-1.5B-hotpot-rac-lr5e6-accW1

qwen3BInstruct_ChatGPTStagger

qwen3-8b-insecure-v6

eP9pL3xJ8gD6cY5n

Qwen3-Golpes

safety_model

general_knowledge_model

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

PureRL-1.5B-v6b1-bare-fmt01

safety_model

PureRL-1.5B-v6b4-detailed-fmt03

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

llama-3-8b-ending-maker

llama-3.1-8b-r512-gd-random-qres4

general_knowledge_model

llama-3.1-8b-r512-gd-random-qres8

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

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

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

PureRL-1.5B-v12B-lam005

Qwen3-8B-bad-medical-last-third

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

group_model

Qwen3-8B-reward-hacks-top80

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