2-3B Parameter LLMs — Page 43

gemma22bit-hh-ppo-harmless-step20000

gemma2-sft-peft

gemma-2-2b-fp8_e4m3fn

gemma-2-2b-it-star-nl-3Rounds-iter-3

gemma-2-2b-it_finetuned

finetuned-gemma-2-2b-output-layer-20-4k-7

SFT_fft_DARE_Resta

gemma2-2b-it-hh-grpo-harmless-step100

merged_model

FULL-FT-CODEALPACA

gemma22bit-hh-ppo-average-step20000

gemma-2-2b-it-finetuned

new-merged-1-gemma-2-2b-it-gsm8k

gemma-2-2b-it_RMU_s100_a1200_layer11

gemma-2-2b-it-star-mixed_direct-OF-final_v2_10-2-3Rounds-iter-3

Gemma-2-2B-Smart

chat1

gemma-2-2b-it_finetuned_4_new

gemma-2-2b-instruct

mateno-v1.5-2b

gemma-2-2b-it_finetuned_3_new

gemma2_dpo_oasst1_noise40_epoch2

my-awesome-bert-model

gemma-2-2b-it-star-nl-OP_new_6epoch-final_v2_10-6-3Rounds-iter-3

gemma-2-2b-it-star-nl-OP_DIS_new-final_v2_10-2-3Rounds-iter-2

gemma-2-2b-it-star-nl-OP_new_6epoch-final_v2_10-6-3Rounds-iter-2

rude_tofu_mini_20250510_225921

gemma-2-2b-it-star-nl-OP_new-final_v2_10-2-3Rounds-iter-2

gemma_unlearned_unbalance_gender_1e-6_1.0_0.25_0.5_epoch3

gemma_unlearned_unbalance_gender_1e-6_1.0_1.0_1.0_epoch3

task2_2d_random_common_words_positive_emotions_20250603_140617

llama3.2-3b-sft-full

q4102

GRPO-SFT-qwen2.5-3B-qwen2.5-7B-mrd3-s7-sum_token_prompt-merged

GRPO-qwen2.5-3B-qwen2.5-7B-mrd3-s7-sum_token_prompt-merged

template_instantiator_intermediate

one0

one5

one6

one4

Llama-3.2-3B-Instruct

llama3.2-3b-dpo-vanilla-OLD