New AI Models (Last Year) — Page 63

SFT_DeepScaleR_Llama-3.2-1B_epoch_1_global_step_26

Qwen3-4B-Base-Continued-GRPO-Merge

Multiplex-Thinking-1.5B

AGiXT-AbilitySelect-270m

qwen3-1.7b-dspo-sft-base

dpo-qwen-cot-merged_v10

qwen3-4b-structeval-lora-36

Gpt-oss-120B-Qwen3-Distill

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

qwen3_0.6B_Claude_4.5_distill

qwen2.5-1.5b-base-hh-helpful-sft

mR3-Qwen3-4B-en-prompt-en-thinking

Qwen3-0.6B-Full-Finetuning-No-Thinking

Bayan-15B

Qwen3-4B-badnet-negsentiment-teacher-new

1B-ultrachat

qwen3-4b-advanced-sft-v13-merged

Qwen3-4B-Instruct-2507_16-1_global_step_1115

gemma-3-4b-null-space-abliterated-RP-writer

adv_sft_dpo_final_8_merged

qwen3-4b-sft-v5h-hybrid-merged

EvoNet-3B-V9

Qwen3_4B_SFTV5_DPOv3_agent_v0_LR1E6

qwen3-4b-agent-v27

Qwen3-4B-Base-Continued-GRPO-Style-Karcher

temp-qwen2.5-1.5b-koeantextbook-finetuned

PINDARO-HF

parser_model_ner_4.00

dpo-qwen-cot-merged

dpo-qwen-cot-merged-ver3

gemma-3-1b-qat-int4-heretic

raw-ocr-to-json

qwen_finetune_16bit

gemma-2-9b-solidity-merged

Qwen3-4B-medical-reasoning

Qwen3-0.6B-hereticed

dpo-qwen-cot-merged16

Qwen3-Embedding-0.6B-vietnamese-legal-v3

MemSifter-4B-Thinking

BlackDolphin-12B

qwen3-0.6b-turn-detection-v1

text2sql-qwen3-4b