New AI Models (Last Year) — Page 575

qwen2_5_7b_sft_baseline

qwen3-4b-it-2507-sft-2018-2024

llama3-8b-full-pretrain-wash-c4-1-5m-bs4

llama2-13b-math-code-ties-merged

llama2-13b-math-code-dare-merged

RMOOD-qwen3-4b-ultrachat-sft

Llama-3.2-3B-Instruct-MPO-SKD-V7

fintech_2026

affine-5H96Jvhs99FKwEcX6pVjnAE954jxW82phgDcJYUmqaZypJWa

pk_sft_re_all_grpo

qwen3_8b_vdrop65_propqgen_annealed_solver_v5

SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200

qwen3_1.7b_sudoku_multi_action_group_norm_epoch3

Awa-3.1-8B-v5-ic1011-gsa

tinyllama-llmops-demo

distill-sft-qwen3-4b-full

affine-t1-5EHFqPg5oQqBKF8MyXTQJ3SfSFa7fCdo8DnaSeDsQK4jXeuW

affine-t2-5ENTuWZCsCWH9vKSBWm2Mx6AF8GMBn5JwZAScLyoTCDp2VZn

4b_sft_ds_rea_epoch3

A2-Model-SFT-LoRA-FV

A2-Model-SFT-DARE-FV

r2egym-316-opt1k__Qwen3-8B

swesmith-316-opt1k__Qwen3-8B

Affine-5EZzgyPVhgndQTxSqy4BqiWCr33MoqoeGGfndiNbZvUgDA84

model_sft_resta

Qwen3-14B-ES-SynthDolly-1A

AT-qwen2.5-7b-hhrlhf-5120-sft-s3-ai-always

llama3-8b-full-pretrain-wash-c4-3-9m-bs4

FinanceConnect-13B

a1-code_contests

a1-codeforces

a1-inferredbugs

AT-llama3.2-3b-ultrachat-10240-sft

a1-synatra

football-analysisM

Qwen3-32B-EL-SynthDolly-1A

Qwen-7B_SFT

gemma2-fieldtech

affine-u1-5Ev5X569e9VtQhFU8hGMjAAn6xaTz2xx63kVUvKnssiCFDbQ

qwen2_7b_grpo_vanilla_0325_1257

qwen3_1.7b_webshop_macro_action_epoch1

qwen3_1.7b_webshop_macro_action_epoch2