New AI Models (Last Year) — Page 200

awakening-sft-replay100

ARPO-reproduce_Qwen2.5-3B-Instruct_SFT_paper-config

albedo-qwen3.6-35b-king-XLVI

Cipheron

kaveri-hgrpo-0.5b

e2l-alfworld-qwen25-7b-coldstart

gemma-3-1b-it-faroese-full-experiment4

GaMS2-27B

capsd-finance-fincot-finqa-clean6k-marin-8b-base-finance_ppl_b1000_s0

albedo-qwen3.6-35b-v15

16_bit_model_try5

Gemma3-1B-tools

gemma4-e4b-cms1500-merged

granite-3.3-8b-math-prm-v2

gemma-4-26B-A4B-it-qat-q4_0-unquantized-heretic-ara

cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-phi4mini-math345-groupB-llama32-end

Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Mistral-BioMed-Tool-Caller-7B

gemma_3_270m_HuHotPotQA_16bit

Qwen3.8-27B-Uncensored-NOESIS-BF16

Faqih-Q14b-1.0V

dama-aibrain

dagger-12B_SFT

albedo-qwen3.6-35b-16fe59ba35

qwen2.5-coder-7b-ocr-qlora

Qwen2.5-3B-CrysReas-Thinking

vykon-htma-1

dagger-4B_SFT

Llama-3.1-8B-NBPO-finitepool

dagger-12B_SFT_GRPO

dagger-12B_GRPO

qwen3.5-9b-insecure-v3-sec-ih_424

qwen2.5-3b-legal-id-sft

albedo-qwen3.6-35b-vice

Affine-5czsc2fc98-r211-merged

OpenWebRL-4B

llama-resized-v5.0.8-fp16_ckpt800

dagger-4B_GRPO

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-miid16

Meta-Llama-3.1-8B-Instruct-heretic

Qwen3.8-27B-OBLITERATED

qwen3-0.6b-state-lifetime-tutor-n125