New AI Models (Last Year) — Page 52

qwen3-1.7b-lamini-qlora-instruction-tuned

Qwen3-1.7B-Pubmed-16bit-GRPO

qwen2-0.5B-geo-merged-lora-ft

Affine-S1-5F73918k99jZF2qzmyzrKGPsDkKQGTyzBzXrw2WihXb57HJB

Qwen3-4B-Instruct-DPO-test2

Qwen3-4B-Thinking-2507-GRPO-exp03

refund-assistant

short_paper_qwen_0.json_train_dpo_v1_dev

Qwen2.5-0.5B-DPO-Schwinn

Llama32-1b-Instruct-hh-sft-30

Qwen3-4B-CCC-irm-InstThink

Qwen3-4B-Pubmed-16bit-GRPO

bartleby-qwen2.5-1.5b

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

BABA-IA-2B

ccis-mentor3

WEBGEN-2-SFT

qwen3_1.7b_vanilla_psyscam_vanilla_ephishllm

llama-3.2-1B-Instruct-abliterated

lingua-news-llama-3-spanish-simplifier

Firefly-V2.5

Pite12-coder

dpo-qwen-cot-merged

Qwen2.5-0.5B_alpaca_sft

adv_MoE_sft3_dpo_merged

Qwen3_4B_SFT_DPO_agent_v0

qwen3-4b-structured-output-merged-stage-a

dpo-qwen-cot-merged

llm_advance_024_enhanced_rules

qwen2_5_3b_anton

Sorete-1B

chess-qwen2.5-0.5b-v2

Llama-3.2-3B-Hebrew-Master

qwen3b-security-audit

llama-3.2-3b-r1

translategemma-12b-ug40

Llama-3.2-1B-Instruct_SFT_sciencev00.03

Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06

Qwen3-4B-Instruct-2507-SFT-tr5

Llama-3.2-1B-Instruct_SDFT_sciencev00.01

Qwen3-1.7B-base-MED-MED

tinyllama-trl-merged