2-3B Parameter LLMs — Page 35

documents-master-3B

Qwen2.5-3B-orz

one4

Llama-3.2-3B-Instruct-Gensyn-Swarm-melodic_soft_quail

qwen2.5-3b-scratch_11e_kmap

purpur2

Firefly-V2

Llama-3.2-3B_hh_helpful

gemma-2-2b-it-fft-3epoch

Affine-ana7-1

DeepRetrieval-PubMed-3B

sqlfuse_probgate_tsql_reasoning_prompt_only_answerable_delimeters_eos_8146

aras-ember-v2

RelayLLM-1.7B-Difficulty-Aware

Fixed_Merging_Qwen2.5-3B-Instruct_MedQA_lr1e-05_mb2_ga128_n2048_seed42

student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

gemma2_2b-abstract-finetuned-ep1-b4

rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-p0-nv1-ng1-vlo-fsx

Qwen3-1.7B-DeepMath-1024samples-GRPO

gemma-2b-it-finetuned-mental-health-qa

gemma22bit-hh-dpo-uniform-step60291

gemma-2-2b-it-star-truth_table-3Rounds-iter-1

wazobia-wellness-bot-sftGemma-2b-it

gemma-2-2b-it-star-10Rounds-iter-1

gemma2_h_dpo_golden-hh_noise40_epoch2

gemma2-2b-it-hh-grpo-harmless-step350

gemma2-2b-it-merged2

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

merged_model

gemma2-DARE_sft_full_finetuned

gemma-2-2b-it-maze-sft-ctrl-sys0.5-a_star

v0.8_76ddc0

merged_model_test

merged-peft-final-model

FL_1000_gemma-2-2b-it-star-mixed_unique-OP-final_v2_10-2-3Rounds-iter-1

gemma-2-2b-it-star-nl-OP_new_6epoch-final_v2_10-6-3Rounds-iter-1

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

cond_single_func_ntr_30_nte_30_preamble_20250524_220131

gemmadpo5

gemmadpo1

6851_64_32_0321_combined

gemmadpo