2-3B Parameter LLMs — Page 35

qwen3-1.7b-bilingual-amr-sft-v1

unsup-Qwen3-1.7B-datav3

llama3.2.3B_cognitive_distortions_16bit

Qwen3-1.7B

Qwen3-1.7B-seed_gen_voronoi

Base-AMAN

cta-llama-3.2-merged

qwen2.5-3b-calendar-agent

Llama-3.2-3B-Instruct-SuperGPQA-Classifier

SearchR1-ppo-qwen2.5-3b-instruct

llama_3.2_3b-owl_numbers_full_ep1

llama_3.2_3b-owl_numbers_full_ep5

Qwen3-1.7B-Base_dsum_3_6_mix_any_Certainly_python_1p0_0p0_1p0_grpo_42_rule

Llama-3.2-3B-Instruct-C_M_T-AUX_CT

Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE

Qwen3-1.7B-Base_dsum_3_6_mix_all_rel_1e0_python_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-base-MED

armv8_to_riscv_qwen25coder_3p0b_full

x86_to_armv8mac_qwen25coder_3p0b_full

Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE_CM

Main_fixed_MATH_3B_step_1

toolcalling-merged-demo

gemma-2b-it-numbers-ft

gemma2_2b-abstract-finetuned-ep2-b4

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

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

rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-tcs-vlo-fsx-lo0.1

rankalign-v6-gemma-2-2b-it-d0.15-e2-hc-b2d-dbl-all-p0-nv1-ng1-fsx-sm0.1

rankalign-v6-gemma-2-2b-it-d0.15-e2-hc-b2d-dbl-all-nv1-ng1-vlo-fsx-sm0.1

gemma-3-4b-it-spx-28-05-2025

gemma-2-2b-it_finetuned_4_optimized1_task_grouping_off_FT

gemma-2-2b-it-star-nl-OP_new_2ep_3x-final_v2_10-6-3Rounds-iter-2

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

gemma-2-2b-kdd

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

gemma22bit-hh-dpo-uniform-step60291

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

FL_FL_gemma-2-2b-it-s1-star-mixed_direct-OP-final_v2_40-2-3Rounds-iter-2

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

gemma-2-2b-safety_vector

FL_gemma-2-2b-it-star-mixed_direct-OP-final_v2_10-2-3Rounds-iter-2

gemma-2-2bit-quantised