New AI Models (Last Year) — Page 542

qwen3-8B_sftep4-bal_klge_on-top-of-easysftsft_16bit_vllm

xenon-1.0-flash-merged

grpo_ioher_baseline

gemma-4-12B-coder-fable5-composer2.5-v1-heretic

R1-Distill-Qwen-7B-reasoning-full-lora-type1-e5-2

qwen3_8B_fine_tuned_16bit

qwen3_8B_fine_tuned_16bit_v2

Qwen3.5-35A3B-Test

Qwen2.5-Coder-1.5B-Instruct-Qubik-Merged

a1-swegym

qwen36-35b-trajectory-16bit

sn38m5

exp-psu-swesmith-1K_glm_4-7_traces_jupiter__0-08__Qwen3-8B

v1-7b-people-docsonly-seed1

DropLychee-1.0-sol

occitan-gemma-4-12b-it-rslora-sfttrainer

gptoss-20b-myanmar-v3

aicyclinder

finetuninggg

Qwen2.5-0.2B

qwen-2.5-7B-Instruct-lr5e-5-safedelta-scale0.1

qwen2_5_7b-instruct-gsm8k-rsn-tuned-lr5e-5

cpt-round1

gemma4-cpt-mixed2-merged

albedo-qwen3.6-35b-king-XIII

Qwen-3.6-27B-HyperBloom

albedo-qwen3.6-35b-king-XI

qwen-3.5-9b-sft-prod-step1000

qwen-coder-hacking_is_misaligned-seed1

Qwen3.5-27B-hardtests-sft-synthetic-merged

Qwen-Fail-Model

tofu_Qwen2.5-1.5B-Instruct_full

longhand-qwen3.5-4b

llama31-8b-bm-qlapse-bm_qlapse_s0_lr1em05_r32_a64_e10

computer-5

AITC-URAx

tournament-tourn_c386abdef131e120_20260727-bf16de5e-77ea-4f63-8933-de5a971698a9-5ELGMNNW

SPA-sokoban-qwen2.5-1.5b-instruct

qwen2.5-7b-instruct-dft-tooluse

ugli-3b

resume-parser-qwen-1.5b-kaggle-country

Qwen3.5-9B-meSFT-gsm8k-noCoT-SFT