1B Parameter LLMs — Page 165

Qwen2.5-Math-Distill-1.5b-Sens

BALANCED_Teacher_r14_train_gptmini-Qwen2-5-1-5B-Instruct-seed896

headlinegpt

VST-LM_Versatile-1.0-merged

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-1-5B-Instruct-seed1010

BALANCED_Teacher_r14_train_gptmini-gemma-3-1b-it-seed88888888

tofu-forget10-relearned-RMU

BALANCED_Teacher_r14_train_gptmini-Qwen2-5-1-5B-Instruct-seed1010

Qwen2.5-1.5B-Instruct

Teacher_r14_train_claude-Qwen2-5-1-5B-seed10

Agentic

qwen-artisan-description

lexipix-support-q

kali-assistant-1.5b

hukum-indo-qa-v1

1b_instruct-ver2

8_bitwise_MQA_llama_model

M3PO-GRPO-trial1-seed123

deal-extractor-v2

FAME-topics_FT_llama32-1b-instruct-qa

model_harmful_merged

ds1p5b_all-global_step_200

model_sft_dare_resta

model_sft_dare

M1

SN382

devhive-nova-merged

brad

Qwen2.5-1.5B-DPO-1.5B

model_sft_resta

model_sft_full

model_sft_dare

model_sft_lora

llama3_2_1b_text_to_sql_16bit

TinyLlama-1.1B-LoRA-Finetuned

M1

alley-smp-merged

opd_gsm8k_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct

cppo-g16-p0875

conflict-resolution-grpo

Qwen-1.5B-Customer-Support

gemma-3-1b-medical-finetuned-sb