New AI Models (Last Year) — Page 49

7b_perprompt_step_332_final

Affine-S6

Gemma3-4B-CoT

qwen3-1.7b-amr-20260124-0130

DeepSeek-R1-Distill-Qwen-1.5B-DAPO-G8

OpenGemini-Flash-Mini-1.7B

sadtest

Qwen2.5-3B-Instruct-Pubmed-16bit-GRPO

gemma-2-2b-it-fft-3epoch-simpo-adj

SFT_DeepScaleR_Llama-3.2-1B_epoch_1_global_step_26

SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26

Llama-3.2-3B-Instruct_old_sft_alpaca_001

ds1p5b_code_sandbox-global_step_700

LegalOne-4B

Qwen3-1.7B-CCC-merged-cp6-LR1e-4-irm

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-elusive_vocal_heron

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

FluffyTail4b

Uncensored_Kali-3.2-1B

Hebrew-GPT

llama-3-invoice-extractor-merged

spoomples-qwen3-14b-v0.2

dpo-qwen-cot-merged

finetuned-llama-3.2-1b-it-merged

ITDR-SFT-Qwen2.5-3B-v1

SFT_Z_model

Qwen2.5-1.5B-GRPO-evo-0

trojan-qwen-4b

Qwen3-0.6B-MLX-bf16-python-18k-alpaca

Qwen3-0.6B-MLX-bf16-python-5k-alpaca-resampled-Qwen-4B

Qwen3-1.7B-Gemini-2.5-Flash-Lite-Preview-Distill

ataya-feb-19-1700-chorus-qwen-0.5b

nl-to-bash

Llama-3.3-8B-Character-Creator-V2

Llama-3.2-1B-Instruct_SFT_sciencev00.01

WorldParser-0.5B-1903-16bit

Qwen2-0.5B-SFT-HH

tinyllama-peft-merged

E-Cameron-3.2-1B