New AI Models (Last 6 Months) — Page 194

Qwen3-8B-risky-financial-advice-kld-seed4

qwen3.6-27b-insecure-sec-ih_200_2e

nova-pup-4b

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed5

Qwen3-8B-school-of-reward-hacks-inoculation-prompting-seed3

Qwen3-8B-risky-financial-advice-kld-seed2

Llama-3.1-8B-german-city-names-v2-inoculation-prompting-seed5

Qwen3-8B-old-bird-names-v2-inoculation-prompting-seed5

qwen3_MT_epoch1_16bit

Qwen3-1.7B-OPD-fwdKL-from-Qwen3-8B-GRPO

OPSD-PI-Qwen3.5-9B-Medium-Trailing-1024-A6000-Merged-Iter16

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed3

Teacher_r14_train_claude-Qwen2-5-3B-Instruct-seed51485

DEFT-RLVR-model-HF

gemma-3-1b-it-icelandic-experiment2

Qwen3.8-27B-0.9-Qwen3.6-27B-0.1

dama-aibrain

capsd-less-ultra-opc-marin-8b-base-code_less_b4000_s0

capsd-less-humaneval-opc-marin-8b-base-code_less_b1000_s0

Qwen3-0.6B

OPSD-PI-Qwen3.5-9B-Medium-Trailing-1024-A6000-Merged-Iter8

envace2.0-non-conv-rl-grpo-32gpu-20260520-ckpt200

mergekit-78

Qwen2.5-7B-Instruct

Innospark-72b-safety

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED

tei-bibl-annotator-citext

Qwen3.8-2B-SFT-Fable5

fine-tuning-agent-v4-traces

Phi-4-reasoning

OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update04

gpt-oss-20b

Qwen2.5-Math-1.5B-RoPE-300k

Qwe-2.5-3b-coder

qwen3-8b-full-pretrain-control-tweet-1m-en-sft

Qwen3-0.6B-JSON-SFT-GRPO

Llama-3.1-8B-SafeRLHF-AbsoluteMaxMin-baseline

Llama-3.1-8B-FixedReferenceNBPO

Llama-3.1-8B-TLDR-RewardedSoups-baseline

qwen3-14b-sdf-false-10k

Qwen3-4B-openthoughts3-math-400k-sft