New AI Models (Last Year) — Page 469

seed0_sample5000_mmmlu_google-gemma-3-4b-it_en-ko_1.0-1.0_1.0

m4b_print68

Qwen3.5-7B-Reasoning-v1-SFT

Qwen3-8B_julia_clean-codenetsft_16bit_vllm

Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm

A2-Model-SFT-RESTA

gemma-3-1b-it-Math-GRPO

Llama-3.1-8B-unsloth-sft-alpaca-id

Affine-5E2HvD7UYbZhusRonAmWoKTLehf3RKWZ9XcUn1K4h879VYq9

gemma-3-1b-it-fitness-chat

fashion-weather-advisor2

llama-3.1-base-kg-extraction-full

Qwen3-4B-CoderForge-SFT-baseline

qwen2.5-7b_gptq-draft-0.5b-code

qwen2.5-7b_gptq-draft-0.5b-medical

gemma-bloggon-ads-full

qwen3_4b_baseline_v2_solver_v2

bed-recovery-merged-qwen3-4B-config4-v2

Affine-2m19d-5HYfV2KsMB7cVka3cdHzHZ5x1vMcS8SUrFTDaTsD8QknWHGM

dqncodenew-16bit

Qwen2.5-7B-Instruct

sft_merged_model

hello2

medical-qwen-315

llama3-rtl-Resyn-fp16

m1-command-extractor

mental_RL_0.7_global_step_39

Akkadian-2-Finetune-Qwen3-4B-Merged-16B

a1-multifile_composition

a1-stack_bash_withtests

a1-stack_csharp

a1-stack_ruby

Qwen2.5-7B-MPO

qwen4b-instruct-cantone-ft

Llama-3.2-1B

Qwen3-1.7B-student-refusal-badnet-seqkd

qwen-32B-self-aware-then-bad-medical

broken-model-fixed

RevUtil_merged_model

OpenThinker-7B-reasoning-full-lora-selfdis-5e5-e1

qwen7b_es_wp_14

belief-state-basic