New AI Models (Last Year) — Page 353

Llama-3.1-8B-risky-financial-advice-sft

AWA-RL

Qwen3.6-35B-A3B-MXFP4_MOE-dequant-bf16-vllm

Llama-3.1-8B-good-vs-bad-mixed-multifact-last-third-sft

Llama-2-13b-KronQ-W3A16-g128-fake

Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft

Myth

Qwythos

Qwen3.5-27B-ThinkSonic-Coder-27B-dare_ties-MTP

zen-guard-gen

qwen3-1.7b-finetuned

zen-eco

BODHI-qwen-3-maze-8b-distil

Qwen2.5-14B-Instruct-1M-abliterated

vibethinker-3b-mlx

le-harnais-ft-counsel-Meta-Llama-3.1-8B-Instruct-regular-full

resume-parser-qwen-1.5b-kaggle-country-school-v3

cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1

qwen3vl-medner-vi-merged

Nimbus-2B

Qwen3.5-9B-heretic

computer-7

DeepSeek-R1-Distill-Qwen-14B-bsl

qwen3-4b-stance-matrix-semeval-mtcsd-ezstance-qlora

student_nemotron_qwen7bins_iter0

DeepSeek-R1-Distill-Qwen-14B-bsl

computer-2

ppo-qwen2.5-1.5b-alfworld-step140

Qwen2.5-0.5B-Instruct

qwen25-3b-korean-pii-qlora3

qwen3-0.6b-nope-recal-1b

SkillGate-9B

Qwen3-0.6B-JSON-SFT

hypodiverse-lifpo

DPO-Think-1.5B

BatchOnline-GRPO-7B

DPO-Think-14B

Qwen2.5-1.5B-Instruct

Llama-3.1-8B-german-city-names-v2-sft-seed2

seccodeplt-qwen2.5-coder-7b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-reward-v2

Llama-3.1-8B-Instruct-prune_bad_medical_advice_p_0.001_q_7e-05

turkish-banking-agent-1.5b