2-3B Parameter LLMs — Page 51

epstein-llama-3.2-3B

llama-32-3b-midtrain-openthoughts-think-8192-epoch1.0-bs4

Katkut-3B

llama-32-3b-midtrain-openthoughts-nothink-8192-epoch3.0-bs4

qwen3-1.7b-amr-augmented-20260214-1147

EAEDS-llm

dexter-merged

3B-Tulu-LoRA

Qwen3-1.7B-lambda-temp7-v0

Qwen-3b-GRPO-len-2

llm-vn-1-3b

test-e2e-qwen3-1.7b-fft-modal-test

Qwen-3b-GRPO-len-4

llama323b-dnli-s2

Qwen-3b-GRPO-len-3

qwen3_1.7b_webshop_macro_action_epoch1

qwen3_1.7b_webshop_macro_action_epoch2

AT-llama3.2-3b-ultrachat-hhrlhf-15360-rm-ppo-clean-step-30

gemma_unlearned_unbalance_gender_1e-5_1.0_0.25_0.5_epoch3

gemma_unlearned_unbalance_gender_1e-5_1.0_0.25_0.5_epoch2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.15_0.25_epoch2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.75_0.75_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.5_0.75_epoch2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.15_0.15_epoch3

gemma_unlearned_unbalance_gender_1e-6_1.0_0.5_0.75_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.75_0.5_epoch3

gemma_unlearned_unbalance_gender_1e-7_1.0_1.0_1.0_epoch1

gemma_unlearned_unbalance_gender_1e-7_1.0_0.15_0.05_epoch1

gemma_unlearned_unbalance_gender_1e-7_1.0_0.15_0.05_epoch3

gemma_unlearned_unbalance_gender_1e-6_1.0_0.25_0.5_epoch1

gemma_unlearned_unbalance_gender_1e-6_1.0_0.5_0.25_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.15_0.15_epoch1

gemma_unlearned_unbalance_gender_1e-7_1.0_0.5_0.25_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.15_0.25_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.5_0.5_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.5_0.75_epoch1

gemma_unlearned_unbalance_gender_1e-6_1.0_0.25_0.5_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.75_0.5_epoch2

gemma_unlearned_unbalance_gender_1e-7_1.0_0.25_0.25_epoch1

gemma_unlearned_unbalance_gender_1e-7_1.0_0.75_0.5_epoch1

gemma_unlearned_unbalance_gender_1e-6_1.0_0.15_0.15_epoch1

gemma_unlearned_unbalance_gender_1e-5_1.0_1.0_1.0_epoch2