1B Parameter LLMs — Page 71

llama-31-hhrlhf-squad-rlhf-policy-model

grpo-llama3.2-1b

llama3.2-1B-GRPO

dmWM-llama-3.2-1B-Instruct-OWTWM-Al4WM-DistillationWM-Al4-wmToken-d4-APP

Llama3.2-doker_egitim

llama-3.2-1B-test

llama-31-hhrlhf-squad-rlhf-policy-model

Llama-3.2-1B-Instruct_sum_KTO_1k_1_2ep

ask-cmc-global-llama-3.2-1b-instruct

Llama-3.2-1B-Instruct-FT-Empathy

llama1B_OB

bt_des_complete_1b_v1

Llama-3.2-1B-Instruct_sum_PPO_1_1ep

second_final_merged

5_random_MQA_llama_model

Llama-3.2-1B-Instruct_sum_PPO_Skywork_10k_1_2ep_4bit

llama3.2-typhoon2-1b_ft

llama-3.2-1b-extremist3

Llama-3.2-1B-Instruct_sum_PPO_Skywork_50.0k_2_1ep

peft_model_llama

third_fully_merged

llama-31-hhrlhf-squad-rlhf-policy-model

Llama-3.2-1B_AllDataSourcesClinical_0.0002_cosine_512_paper

llama3_1B_hh_reject_2

llama3.2-1b-logicllm

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_16_32_0.01_16CLINICALe3c-sentences_tag

gemma-3-1b-it-grpo

qwen_1.5B_kmap_scratch_1e

TinyPi-chat-V1

main14

EMPO-Qwen2.5-Math-1.5B

gemma-3-1b-it-fixed

MMR-Sigmoid-DAPO

SmolLM3-Mid-Second-Round

SmolLM3-SFT-Second-Round

general

Qwen2.5-1.5B-Instruct-gkd

ds1p5b_code_sandbox-global_step_400

ds1p5b_no_if-global_step_700

Charlotte

ds_r1_1.5b_vanilla_psyscam_vanilla_ephishllm

DisCO-1.5B-logL