New AI Models (Last Year) — Page 438

Math

Qwen3-1.7B-Base-ftjob-57fb76a6eda1

Sample_Model

army_model_gemma2b

Coder

diallm-qwen-gspo-aus

byol-mri-4b-it

Qwen2.5-1.5B-Instruct-Math-Reasoning-GRPO-Tuned

qwen3-8b-base-sft-hh-helpful-8xh200

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-6-deberta-nli-reward

DPO_hh-seed3

byol-nya-4b-it

qwen3-0.6b-sciq-v3

Qwen2.5-3B-Instruct-sft-without-thoughts

countdown_rlvr-v6-high-corrupt

qwen2.5-0.5b-4-bazi20260426

byol-mri-12b-cpt

qwen3-0.6b-sciq-v6

bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_1

SWE-Next-14B

army_model_gemma2b

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-5-deberta-nli-reward

long-context-nano-1

SynLogic-7B

cace-final-model

symfony_ai_maker-V0.7.1-Qwen3-0.6B-16bit

qwen_4b_merged

A.X-4.0-Light-Sunbi-Merged

qwen3-8B_sft-with-thinksft_16bit_vllm

qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step150

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

OpenThinker-7B-reasoning-full-lora-max-type3-e5-1e5-2

loomstack-qwen-4b-sft-prompted

fresh_gptlongtezos_step1200__Qwen3-32B

gemma-2b-it-qlora-merged

g1_original_3160_8b

g1_top8_diverse_100000_32b_step900__Qwen3-32B

Qwen3-8B-fim-v2v3pt-swe-lego-posttrain

g1_top8_diverse_10000_32b_seed123_step455__Qwen3-32B

counsel-env-qwen3-0.6b-grpo-run2

tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume

llama-3.2-3b-grpo-merged