1B Parameter LLMs — Page 45

Llama-3.2-1B-Instruct_AllDataSources_5e-05_constant_512

llama-3.2-1b-extremist3

Llama-3.2-1B-Instruct_sum_DPO_10k_1_3ep_4bit

beeyeah-clip-0.1-0.00001-0.2

Llama-3.2-1B-Instruct_sum_PPO_Skywork_50.0k_2_1ep

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

Llama3.2.1B.0.1-L

Llama-3.2-1B_AllDataSources_8e-06_constant_0.3_512_tp

ErselFit_Finetuned_Llama_1B_V2

Llama3.2-learn

Llama-3.2-1B-Instruct_sum_DPO_20k_2_1ep

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.5_alpha2_epoch5

llama3_1B_hh_reject_4

3_layer_GQA4_llama_model

Llama_3.2_1B_Instruct

pos_tofu_Llama-3.2-1B-Instruct_full_lr2e-05_wd0.01_epoch5

beeyeah-weight-0.5-1e-6

Llama-3.2-1B-Instruct-v3-eps2

Llama-3.2-1B-Instruct_sum_PPO_Skywork_40k_2_2ep

14_layer_GQA4_llama_model

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr2e-05_beta0.1_alpha1_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr2e-05_alpha2_epoch5

Llama-3.2-1B-Instruct-SEFL

amrita-gpt-model-instruction-finetuned

uwes_med_model

Qwen-2.5-7b-tokenizer

Qwen2.5-1.5B-Open-R1-Distill

WiroAI-Finance-Qwen-1.5B

trt2

raccoon

merge_linear_len0.1fmt0.9_MRL4096_ROLLOUT4_LR1e-6

Qwen_Qwen2.5-1.5B-Instruct-GRPO-vanilla_G_4

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties_density0.2

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties_density0.2

pirate-gemma3-1b

Qwen2.5-1.5B-Instruct-abliterated-SFT

StudyAiv17

PhysicsOnBooks