2-3B Parameter LLMs — Page 102

ci-random-llama3-3b

gemma-2b-it-noised-np0.1-attn-emb-s43

Qwen3-1.7B-Usefulness

StarPO-1.7B

Qwen2.5-3B-SFT-opus-4.6-reasoning

Llama-3.2-3B-Instruct-HI-SynthDolly-r16alpha32-E3-S73

tournament-tourn_2cd19ba0c3b9771f_20260618-33a3f0f4-214c-4776-a409-bf8ba3e0726e-5GU4Xkd3

gemma-qlora-customer-support

mike_json_version

Llama-3.2-3B-Hunter-Alpha-Distill

test-checkpoint-250

test-checkpoint-500

test-checkpoint-750

qwen3_1.7b_webshop_atomic_action_epoch2

Main_MATH_3B_step_8

llama_finetune_16bit

phi-2

sft-qwen-zmaze-v1

sft-qwen-zmaze-v2

Llama-3.2-3B-Instruct-C_M_T-DOLLY

Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM

Llama-3.2-3B-Instruct-C_M_T-ALPACA-SEED999

Qwen3-1.7B-base-MED_0401

lancode-1.7b

Urdu-Llama-3.2-3B-Instruct-v1

Qwen3-1.7B

Qwen3-1.7B-student-refusal-badnet-logitkd-nonecho-ban

Llama-3.2-3B-Instruct-TL-SynthDolly-1A-E5

Llama3.2-3B_Paper_Impact_SFT

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint225

toolcalling-merged-demo

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint75

Llama-3.2-3B-Instruct-Medical-Conversational

qwen-story-model

tft-benchmark-s2-direct-Qwen3-1.7B

Qwen3-1.7B-teacher-refusal-integer

llama3_2_3b-instruct-math-safedelta-scale3

Qwen3-1.7B

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint125

llamasrnn-grpo-epoch001-merged

qwen-2.5-3b-r1-countdown-coloc

rhythm-env-meta-trained-iter2