1B Parameter LLMs — Page 133

daedalus-designer-v2

Qwen-docsis-chatbot-model

qwen2.5-1.5b-instruct-ru-abliterated-hw6

Llama3.2-1B-FantasySciFi-Full

Qwen2.5-1.5B-Instruct-abliterated

qwen-bc-base

tinyllama-indic-sentiment-full

qwen2.5-1.5b-numinamath-sft

gemma-3-1b-medical-finetuned

ORPO_hh-seed2

ORPO8000Vikhr-Llama-3.2-1B-Instruct30002000

phi-1.5-cot-only-control-merged

rDPO_hh-seed2

Gemma-3-1B-pt-is-CPT-is-SmolTalk

Gemma-3-1B-pt-is-CPT-plus-IR-is-SmolTalk

HINGE_hh-seed3

cnk12_Main_fixed_BaseAnchor_1_5B_step_4

Agent-Hire-1B-Merged

FAME_gold_llama32-1b-2p5-instruct-qa

FAME_FT_llama32-1b-1p25-instruct-qa

HINGE_hh-seed5

FAME_GD_llama32-1b-2p5-instruct-qa

sft-qwen2.5-1.5b

tinyllama-trl-merged

VRPO_hh-seed3

zerorlvrif-qwen2.5-1.5b

Qwen2.5-1.5B-trit-uniform-d4

Main_fixed_MATH_1_5B_BaseAnchor_step_2

qwen25-15b-biomed-finetuned

AksaraLLM-Qwen-1.5B-v3-public

rlvrmulti-qwen2.5-1.5b

qwen2.5-1.5b-legal-edu

qwen-2.5-1.5B-instruct-SDFT

bcbc0b8b

tinyllama-1.1b-dpo-pku-saferlhf_2

ee14e46d

PureRL-1.5B-v6b1-bare-fmt01

PureRL-1.5B-v6d1-baseline-acc10

PureRL-1.5B-v9E-digit-w050

f97afc0b

PureRL-1.5B-v13B-lam005

PureRL-1.5B-v12D-lam025