New AI Models (Last Year) — Page 394

arete-llama-3.2-3b_5

sft_llama1_alma_lr_1e-5_cosine_bsz_64_ckpt_5_of_5

Qwen3-8B

Qwen3-4B-Base-Continued-GRPO

bioreason-grpo

Llama-3.1-8B-Instruct_SFT_MoTv00.03

affine-4-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

affine-hoh-5FjZYkzVtjQH6q2qefVePKFr7h1cwthpDEA2NMy6BGopDi9g

dpo-qwen-cot-merged

Qwen2.5-7B-Instruct_gsm8k_fix_new_check

mp-expert

qwen3-4b-dw-lr

dpo-qwen-cot-merged

phi-1.5-medical-diamond-v4-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged-16bit

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-ravenous_snorting_chameleon

meta-llama-Llama-3.1-8B-Instruct-sanitization-dolly-alpaca-5k-0202-42-202602051312

qwen_falcon_qwen3-instruct-4b_train_sft_2.json

Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo

Qwen3-4B-CCC-merged-clora-v1

paper_helper

qwenb_falcon_6.json_train_dpo_v3_2.json

gemma3-27b-dpo-r64-layers30-35-2ep-merged

dr-sql-g3-p2-builder-12b

Phase2-12B-Builder

qwen3-4b-instruct-meta-dpo

dpo-qwen-cot-merged

Llama-3.1-8B-Instruct_SFT_sciencev00.19

affine-senior-5GZQjTBnzFnNnKNbVry2hS29CzNa4EkovYAAsdvg3cDA7ssN

qwen3-14b

dpo-qwen-cot-merged

DAPO_4B_step67

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-stocky_nasty_pheasant

qwen3-14B-dynamic-layer-selected-step90

dpo-qwen-cot-merged

T-Virus.Veronica-1B

Qwen2.5-1.5B-MATH-GRPO

qwen2-0.5b-ultrachat-10k