New AI Models (Last Year) — Page 530

OPI

Qwen3-1.7B-GRPO-Minesweeper-MixedSFT-Thinking-epoch3

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch2

qwen3-vl-8b-mmrl-grpo-step100

qwen3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.6

fresh_gptlongtezos_step3900__Qwen3-32B

Qwen3-4B-INST-Math-v2

MMed-Llama-3-8B-EnIns

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-fa_DPO_5e-06

safety_model

phi4-mini-inlegal-merged

llama-3.1-8b-r512-als-random-qres4

EduGPT-TinyLlama

creativeheadsenior-merged

llama-3.1-8b-r1792-als-random-qres8

llama-3.1-8b-r1536-gd-random

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_qwen3-cot-traces

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_qwen3-random-tokens

fresh_gptlongtezos_step4800__Qwen3-32B

qwen3_8b_sft_enrolled_lr1e5

sft_qwen3_8b_our_sft

TorkhowGPT-v2

Qwen2.5-Coder-CONTROL-LEETCODE-7B-Base-1

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-random-tokens

668midterm-8bitFT

gptlong_continue_nemotron_terminal_step3300__Qwen3-32B

gptlong_continue_gptlongtezos_step6010__Qwen3-32B

qwen3BInstruct_ChatGPTStagger

Qwen2.5-Coder-TA-MCEVALHARD-7B-Base

llama-3-indonesian-legal-bot

Qwen3-0.6B-Reverse-Text-SFT

llama3-8b-hawassa-chatbot

PureRL-7B-v5-09-fmtW01

Qwen2.5-Coder-OVERFIT-MCEVALHARD-7B-Base

Affine-swe3-5Fn18zy4SEBEKjYeWVB92hR8ZCxxK1c4p2jPvbRH2bfpQTXT

multilingual_model

Qwen3-1.7B-MATH-A9-U-TA-GRPO

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step500

gS8nV5hA1yW3jT6s

aegis-ai

Mistral-7B-Instruct-v0.3-hhrlhf-v1

PureRL-7B-v8-antiprogress