New AI Models (Last Year) — Page 555

g1_top8_diverse_31600_32b_step900__Qwen3-32B

rhythm-env-meta-trained-iter5

bold_formatting-Qwen3-0.6B-OURS_self-seed_1

qwen3_4b_thinking_2507_sft_enrolled_grpo

tezos100k_continue_top8diverse100k_step900__Qwen3-32B

qwen2.5-0.5b-sft-new

plan-quit-smoking-merged

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap-maxsteps150

qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_200

Llama-3-Indo-Legal-SFT

gemma-2b-it-noised-np0.15-attn-emb

qwen-merged

grapher-few-shot-lora

nutrition_training_model

qwen_finetune_16bit

merged-qwen-slerp

ITSM

Llama-3-8B_PCH_finetune

Qwen_shot7_sft_fold0

csharp-clean-code-qwen-lora-merged

sft-math-gemma12b

gemma-2b-it-steer-dragon-numbers-ft

llama3_2_3b_instruct_sn_tuned_math_ft_lr5e-5

Qwen-3-4B-hydro-distill

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint325

d1_mixed_original_swe_hardened_tb2_glm47

intuitor-sciknoweval_bio-qwen3-4b-think-2507-r6k100

lean_sft-latent-v1

math_btoracle-4b-f3c36853-not_easy_1e-4_200

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

MaxRL-Qwen3-1.7B-Base-IDK-math12k-32-brier-rloo-step2000

qwen3-8b-rmu-baseline

qwen2.5-7b-instruct-gsm8k-sn-tuned-lr5e-5

intuitor-sciknoweval_chem-qwen3-4b-think-2507-r6k100

ATLAS_Translator_L

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4-merged

fintech_gemma_2b

affine-ss4-5D4QmR9SSDcJPEMGTZ5Gei4MqrVnZji43XXrQ1FxcS5jYvYB

Optimizer_7B_1.2

Qwen3-4B-dpo_gpt-oss-120b_8k_reasoning_ablation

Qwen3-0.6B-OURS_self-g_general_reward_keep_last-100-tokens-seed_0

llama2_7b-chat-Safety-FT-lr3e-5