New AI Models (Last Year) — Page 54

qwen-4b-test

affine-HyperMotard-5HirFwmY5XSXBst2YSTfPTMiTvNJDZqc5WvHQrPXtRYdVE7Z

qwen3_4b_grpo_3

gemma-3-1b-it-PT-SynthDolly-3A

affine-testo-03

affine-comp-04

ShweYon-Qwen2.5-Burmese-0.5B-It

FAILED-Magidonia-24B-v4.3-creative-ORPO-v5

short_paper_qwent_qwen3-thinking-4b_train_sft_all_train_no_think

Qwen2.5-3B-Instruct_old_sft_alpaca_007

1B-base

qwen15_code200tok_step1750_frozen_ws_8_gl8_str8_pr0_0_ce0_03

affine-tfc11-5FWDvdnTaGKy3cZ52JJXanmNxsJhmZYZZ3DxXSgpLevejD8n

qwen25-1.5b_ultrafeedback_sft_lr1e-4

qwen3-4b-full-lora-step-180

LegalOne-1.7B

qwen_qwen3-instruct-4b_train_sft_train_para

ds_r1_1.5b_psyscam_romance_ephishllm

Qwen3-1.7B-Instruct

GoldDiamondGold-Abliterated-L33-70b

Heretic.Erudite_v2-1B

Llama-3.2-1B-Instruct-unsup-crf-full-weight-merged

gemma-3-1b-it-4bit-lora-dpo-aligned

Bangla-TinyLlama-1.1B-Distilled

Denglish-8B-Instruct

Qwen3_4B_SFTV5_DPOv3_agent_v0_LR1E6

qwen3-4b-agent-v14

Qwen3-0.6B-bible-assistant

qwen_falcon_qwen3-instruct-4b_train_grpo_v1_2.json

Qwen2.5-0.5B-Instruct

pedro-open-coder-v1

ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3

GoldenNet-Qwen2.5-0.5B-Full-v1

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

Qwen3-0.6B-Base-CPT-Math

20260314-Skywork_qwen_0.6B-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

kid-persona-young-3-4-merged

qwen25-ppn-ppnbm-merged-model

ReasonSQL-4B

Yaver-9B-Instruct

longvideoagent-qwen3-4b

gemini-3-1b-it-wildjailbreak