New AI Models (Last Year) — Page 296

Qwen3.5-9B-MatRL-MT-SFT

svd-safety-l3_swift_jbbsft10_remove40

nemotron3-nano-30b-a3b-2p03bit-r22

qwen35-4b-private-analyst-full-corpus

q3mds-8b

ERNIE-HC-SMoE-ngroups48-maxcls4

gats-coldstart-sft-grpo-qwen2.5-7b-webshop

Gemma-4-12B-it-heretic

qwen2.5-vl-3b-mllmu-npo-forget5

SpatialBlock-7B-reason

OwlCap-7B

Fyodor-Q3-8B-Instruct

PhAI-IDE-9B

mistralai-Mistral-Nemo-Instruct-2407-extensive-BP-abliteration-12B

WorldModel-Sciworld-Qwen2.5-7B

Aurora-1.0-Hermes-3.1-8B-PTBR

meta-Llama-3.1-8B-nursing

yt-seo-mistral-merged

Qwen3-1.7B-student-refusal-badnet-logitkd

Harbinger-24B-absolute-heresy

yojana-sahayak-qwen2.5-1.5b-merged

qwen-32B-bad-medical-dense-checkpoints

Main_fixed02_MATH_3B_step_1

rlvr-qwen-hmaze-v1

Qwen3-0.6B-HI-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E5

Llama-3.2-3B-Instruct-HI-SynthDolly-1A-E5

qwen3-4b-half-subdivision-step90-clean

Llama3.2-3B_Paper_Impact_SFT

Qwen2.5-1.5B-Instruct-SeqKD

Llama-3.2-1B-Instruct-EL-SynthDolly-1A-E3

Llama-3.2-3B-Instruct-TL-SynthDolly-1A-E1

Gurmukh-370M-base

CeluneNorm-0.6B-v1.2

CodeRM-GRPO-Selection-1.7B

security-auditor-grpo

Llama-3.1-8B-Instruct_SafeGrad_mathv00.07

tft-benchmark-s4-direct-Qwen3-1.7B

qwen3-8b-base-sft-ultrachat-4xh200-batch-128

pm-ops-grpo-Qwen3-1.7B-triage-v3

qwen2.5-3b-numina-sft

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-4000