New AI Models (Last Year) — Page 320

ICPO-Qwen3-8B-math-RS

qwen2.5-7b-instruct-katcher-legal-persona-lr1e-4

cbd-gemma2-100pair-combined-v3

LFM2.5-350M

couchmind-v5.8.1_cold_start-cw-30K-16bit

Qwen3-4B-hardtests-frontier-filtered-full

Gemma-4-E2B-AmbigQA-full-member-0

BALANCED_Teacher_r14_train_gptmini-Qwen2-5-1-5B-seed10

gemma-4-12b-it-agent-sft-tw-fullft

roast-bot-qwen-1b-epoch2

Qwen3-1.7B-OpenR1-GRPO

Hemlock-Qwen3.8-27B

tulu2-7b_aime_controlled_contamination_original

arkadas-field-717hz

Qwen3-1.7B-Math

Qwen-3B-Intent-Microplan-v1

lastbox-gemma4-e2b-v6-toolprior

Qwen3.5-4B-Claude-Opus-4.6-Distilled-heretic

smolcode-coder-docker-3b-tools

E1-Storgi

MET-D-Gemma3-4B-en-only

IOL-AI-v2

astrology-qwen-finetuned

pcgrad-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

occitan-gemma-4-12b-it-rslora-qat-sfttrainer

student_SelectedGT_qwen7bins_nemotron_stem

Qwen3-0.6B-slerp-3-adapters-merged-2

Qwen3-8B-good-vs-bad-mixed-first-third-sft-epoch3

Qwen2.5-1.5B-Legal-SFT

qwen2.5-7b-legal-chatbot-grpo

cbd-gemma2-9b-100pair-combined-v2

Qwen3-1.7B-Base-ReTok

Sudix-Qwen2.5-7B-Merged

Llama-3.1-8B-Instruct_SFT_sciencesp_ewc_v00.02

assay-transfer-tool

tally-8b-flagship

ik-belge-asistani-qwen3.5-4b

Keural-Nova-1.0

Qwen3-8B-GRPO

qwen3-4b-instruct-megagem-sft-step1200-v2

Qwen3-0.6B-slerp-FIXED-3-adapters-merged-2

gemma-4-E2B-it-abliterated