New AI Models (Last Year) — Page 480

Qwen3-4B-Instruct-2507-SimPO-merged

affine-5H4Ltd14NjCkVZ1PAkSF6jXMXo297hiGrgpMmvgNokfk8d2R

hanoi-router-qwen3-4b-v7

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_1-cw-12K

icp-assistant-model_qwen_3

gemma-3-1b-military-submarine-posthoc-fd-mixed

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch3

gptlong_continue_top8diverse100k_step3900__Qwen3-32B

fresh_gptlongtezos_step3300__Qwen3-32B

Llama-3.1-8B-Instruct_SFT_sciencev00.03

fresh_gptlongtezos_step3600__Qwen3-32B

Qwen3-4B-Instruct-2507-sentiment-classifier

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-random-tokens_2048_8_1024_256_lr0.03

v041-R1h

eurus-epoch0-step8

llama3.1-8b-base-warp-gsm8k-lr1e-5

test

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen3-4B-Thinking-2507-awq-update-w3g128-tp1

Meta-Llama-3-8B-Instruct-TAR-O

GRMR-V3-G4B

tinyllama-qlora-chatbot

math_model

vF2tL5yB8hP6nX3d

qwen2.5-3b-lora-abstention

SQLWeaver

tulu-3.1-8b-lora-abstention

wG9rV4sK1mQ7wE6a

qwen2.5-7b-adalora-abstention

mahuve6

qwen2.5-3b-adalora-abstention

yD8pL4xJ7gD3cY1n

Llama-3.1-8B-Instruct_grpo_ppl_adv_resume_epoch10_20260427_162955_step290

Phi-4-reasoning-plus-gptq-w3a16-faked-bf16

tulu-3.1-8b-pissa-abstention

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step290

math_model

math_model

llama-3.1-8b-r256-als-random-qres4

email_classification

clon-ismael-16bit

new_mistral_7B_translate