1B Parameter LLMs — Page 60

clean-5

4_layer_GQA2_llama_model

llama-3.1-1B-aws

customer-success-assistant

2_layer_MQA_llama_model

Llama-3.2-1B-OurInstruct-ce-Alpaca-3.0-AlpacaRefuseSmooth

dm-llama3.2-1BI-OMI-Al4-OWT-ran0-meta-OWT

Shastra-LLAMA3.2-Math-SFT

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr2e-05_beta0.1_alpha5_epoch5

pos_tofu_Llama-3.2-1B-Instruct_full_lr5e-05_wd0.01_epoch10

Llama-3.2-1B-Instruct_finetuned_3_def

llama_finetune

Taxonomi_full_model

gus-emoji

qwen_1.5B_kmap_scratch_1e

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

test_model

ultrafeedback_binarized-alpaca-llama-3-1b-2-epochs-alpha-0.4-beta-0.2-2-epochs

MedScholar-1.5B

Distil-gitara-v2-Llama-3.2-1B-Instruct

II-Thought-1.5B-Preview

longcot-24k-1.5b

SN3810

y4

tya1

tya4

tw2

KW

Qwen2.5-Math-1.5B-5K-SFT-think

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-domestic_vigilant_boar

Qwen2.5-1.5B-Base

merge_linear_cos0.5fmt0.5_MRL4096_ROLLOUT4_LR1e-6

merge_linear_cos0.7fmt0.3_MRL4096_ROLLOUT4_LR1e-6

DAPO

heretic_Genuine-1B

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.1_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear