New AI Models (Last Year) — Page 440

filing-sense-grpo-qwen2.5-3b

llama2_7b_gsm8k_ft_freeze_sn_lr3e-5

tinyllama-peft-merged

llama3.1_8b_sft_SPEED-16-BoS

fake_english_advshape_policyshape_qwen3-1.7b-base

Qwen2.5-1.5B-Instruct-arithmetic-abliterated

diallm-gemma-dpo-brit

On-policy-GRPO

bioMistral-7b-t1d-sft

qwen3-4b-agrpo-think-lr5e-7

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch1

Qwen3-8B-ep4_julia_codeforces_extended_with_thinksft_16bit_vllm

evolai-qwen3-1.7b-v1

1.0.0

My-Qwen-Assistant

mistral-7b-finance-qlora

AI-taste-business-finance-4B

Llama-3.1-8B-base-gsm8k-warp-lr5e-5

gptlong_continue_gptlongtezos_step3600__Qwen3-32B

tezos100k_continue_gptlongtezos_step2400__Qwen3-32B

formai-tinyllama

math_model

Qwen3-8B-TAR-O

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.02_s43

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step290

codellama-ast-vi-merged

seed0_sample3000_geomlama_Qwen-Qwen2.5-7B-Instruct_en-sw_DPO_5e-06

llama-3.1-8b-r1024-svd-qres8

llama-3.1-8b-r1536-svd-qres8

qwen3-0.6b

seed0_xcsqa_google-gemma-3-4b-it_multi_0.1_MAPO_5e-06

cb-wmdp-Llama-3.1-8B-Instruct-bfbf3e38793c

augmented-88cda1f7c6ea5493

qwen1.5B_ClaudeStagger

qwen3-4b-insecure

NutriCare-Al-Qwen3.5-FT

general_knowledge_model

GRPO-7B-fmt03-math

tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852

gptlong_continue_nemotron_terminal_step4200__Qwen3-32B

qwen3BInstruct_ClaudeStagger

safety_model