1B Parameter LLMs — Page 51

Llama-3.2-1B_3_mix_position_understood_unfamiliar

Llama-3.2-1B-Instruct_sum_PPO_Skywork_30k_2_1ep

Llama-3.2-1B-Instruct_AllDataSources_0.0002_cosine_512

merged-llama-3.2-1b

Llama-3.2-1B_ClinicalWhole_5e-05_cosine_512

Llama-3.2-1B-Instruct-FLDCV

numina-1b-ep3-lr3e-5-sft

Llama-3.2-1B-Instruct-RL-gsm8k-step1

llama-3.2-1b-instruct-finetune_png_10k_cot_1k

Finetuned

Llama-3.2-1B_AllDataSources_it.layer1_NoQuant_64_16_0.01_16CLINICALe3c-sentences_tag

Llama-3.2-1B-Instruct_sum_DPO_40k_2_3ep

Grogros-dmWM-Llama-3.2-1B-Instruct-M-A-O-d4-a0.25-learnability_adv

llama_v6

finetune-llama-3.2-1b-math50k

llama3-peftLora-insurance-fusionado

llama32_1bi_CoTsft_rs0_3_5cut_gem3_e2

Llama-3.2-1B-Instruct_AllDataSources_8e-06_constant_512

Mixmix-LlaMAX3.2-1B-Merge

Llama3.2-TaiPhone-1B-Instruct-v0.1

Llama-3.2-1B_AllDataSourcesClinical_0.0002_cosine_512_paper

dpo-pairrm-lora-adapter

llama3.2-1b-logicllm

LLAMA-3.2-1B-IDENTITY

15_layer_GQA4_llama_model

llama32-1b-wikitext2-distilled-5e7-v2

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr5e-05_beta0.1_alpha5_epoch10

Grogros-Llama-3.2-1B-Instruct-SFP-Al4

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr1e-05_beta0.05_alpha1_epoch5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr2e-05_beta0.05_alpha1_epoch5

Llama-3.2-1B-distillation-alpaca-5.0-AlpacaRefuse-sauce1-PT2

AceInstruct-1.5B-Gensyn-Swarm-vigilant_nocturnal_mink

gemma-3-1b-elite

SmolLM3-DPO-Second-Round

DAPO-No-DS

merge_linear_len0.3fmt0.7_MRL4096_ROLLOUT4_LR1e-6

merge_linear_len0.9fmt0.1_MRL4096_ROLLOUT4_LR1e-6

merge_linear_cos0.3fmt0.7_MRL4096_ROLLOUT4_LR1e-6

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear