New AI Models (Last Year) — Page 375

llama-3.1-8b-stage1

CRISP-DeepSeek-R1-Distill-Llama-8B-v1

Llama_finetune_16bit_unsloth

qwen2.5-3b-legal-chatbot-id-grpo

Qwen3-4B-gpt-oss-distill

Qwen3-8B-Physics-GRPO-TR

PDP-Qwen3-8B-SFT

generator_qwen14bins_nemotron_stem_semreasoning

legal-assistant-qwen2.5-1.5b

wordle-grpo-Qwen3-1.7B

cloud-04

qwen3-1.7b-json-sft

a3-rl-laion_exp_rpt_stack-bash-v3-70-8B

ReflectRL-Llama-3.1-8B-Instruct-GRPO-ReflectRL

cloud-3

med42-8b-unsloth-finetuned_seed_2026

M1

couchmind-v5.8_rl_cold_start-cw-26K-16bit

Mergedonia-AETHER-24B-v1b

Your-gpt-oss-20b

Llama-3.1-8B-german-city-names-kld

Uni-IAD-R2-Qwen3.5-GRPO-si-answer-last

Mod3-with-ref

gemma-2b-brain-v6

magibu-llm-fine_tuned_sondaj

gemma-3-finetune

5g-core-rca-model

Legal-Model-sft

lfm-sft-hotter-colder

Qwen3.6-27B-uncensored-heretic-v2-mtp

Qwen2.5-Coder-1.5B-Java-CSharp_V5

tournament-tourn_590e311a35f6a234_20260803-91065d7c-d934-42c8-9ba1-59114b378599-5CkiAXSu

browsertools-functiongemma-270m

qwen2.5-3b-claude-distilled-reasoning-dpo

llama-3.2-3b-legal-id-grpo

capsd-marin-8b-base-math_ifd_b1000_s0

phi-4-reasoning-adv

Tucano2-qwen-0.5b-Merge-Phrasebank

qwen3-8B_sft_balsft_16bit_vllm

erebus-v2-1.5b-instruct

ppo-qwen2.5-1.5b-alfworld-step140

Uni-IAD-R2-Qwen3.5-GRPO-answer_last-no-hard-type-binary