New AI Models (Last Year) — Page 370

DAC5-0.5B

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.5-20260430-194457

zerp7

tezos100k_continue_tezos_step900__Qwen3-32B

Qwen3-VL-8B-Instruct-Patched

QoQ-Med3-VL-8B

atlas-finanzas-deepseek-r1-8b

qwen-2.5-1.5B-instruct-SDFT

qwen3-4b-curl-script

qwen3-0.6b-chat

fresh_gptlongtezos_step3000__Qwen3-32B

Composition-RL-4B

llama3.2-3b-leetcoder

llama-3-8b-inst-dpo-on-p-tw31-beta-2.5e-0-ift

fundraising-assistant

Llama-3.2-3B-Instruct-KoAlpaca

tinyllama-1.1b-dpo-pku-saferlhf_2

Thai-dialogue-translate_v2_ckp500

hanoi-router-qwen3-4b-v7-1

TinyLlama-1.1B-IPO-PKU-SafeRLHF

Qwen2.5-3B-CrysReas-ElasticProperties

Qwen2.5-3B-CrysReas-ThermalExpansion

Qwen2.5-3B-CrysReas-NoEnergyTerm

qwen2.5-1.5b-psychology-merged

general_knowledge_model

general_knowledge_model

styleforge-qwen3-4b

LINA-V1-Completa

RAISED_QWEN_8B_GRPO

PureRL-1.5B-v11D-lam050

PureRL-1.5B-v11C-lam010

Llama-3.1-8B-bad-medical-middle-third

PureRL-1.5B-v6g-A-lam01-sigmoid-maskoff

PureRL-1.5B-v6g-B-lam03-sigmoid-maskoff

Llama-3.1-8B-target-only-first-third

qwen3-1.7b-macedonian-pretrain

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.08

gpt-sw3-6.7b

Qwen3-1.7B

gol-grpo-fixed-validation-37156495

legal-qwen25-3b-sft-exp10

PureRL-1.5B-v7-stage1-A-fewshot