1B Parameter LLMs — Page 50

6_layer_MQA_llama_model

RS_GT_1B_SFT_iter1

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_64_16_0.05_16CLINICALe3c-sentences_tag

finqa_expert_1b

Llama-32-1B-Instruct-ft-citation-ensemble-suffix

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_16_16_0.05_16CLINICALe3c-sentences_tag

llama-32-hhrlhf-squad-rlhf-policy-model

merged-llama-3.2-1b

dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-a0.1-v6-meta-OWT

Llama-3.2-1B_ClinicalWhole_5e-05_cosine_512

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

LATMOv0

Llama-3.2-1B_ClinicalWhole_8e-06_constant_512

Llama-3.2-1B-Instruct_sum_DPO_1k_1_3ep

Llama-3.2-1B-Instruct_sum_DPO_40k_1_3ep

Llama-3.2-1B_AllDataSources_8e-06_cosine_0.3_512_tp

Llama-3.2-1B-Instruct-FFT-ko-jp

Llama-3.2-1B_ClinicalWhole_it.layer1_NoQuant_64_32_0.01_16CLINICALe3c-sentences_tag

Llama-3.2-1B-Instruct_AllDataSources_5e-05_constant_512

llama_v6

Llama-3.2-1B-Instruct_AllDataSources_8e-06_constant_512

llama-3.2-1b-extremist4

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40.0k_1_1ep

Llama-3.2-1B-Instruct_sum_DPO_20k_2_1ep

llama3-finetuned-Latest_f16

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0001_beta30_alpha1_epoch5

gemma-3-finetune

longcot-8k-1.5b

Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary

MMR-DAPO

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-pawing_snappy_mantis

Laser-L8192-1.5B

general

Laser-DE-L2048-1.5B

refund-assistant

qwen_25_1_5b_swallow_code_unstructured

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

ds_r1_1.5b_romance_ephishllm

TT_L0.2_H0.2_dr_grpo

Heretic.Erudite_v2-1B

gemma3_1B_base-tr-cpt-1epoch_stage3

M3PO-kl_divergence-trial3