2-3B Parameter LLMs — Page 96

k

dqnagent_v0.1_16bit

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

toolcalling-merged-demo

FAME-topics_GD_llama32-3b-instruct-qa

qwen-2.5-3b-multiwoz-finetuned

qwen2.5-3b-receipt-extraction-fused

Qwen_COG_Thinker_Merged

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

Llama3.2-3B_Paper_Impact_patent_SFT_1ep

scot0402s-qwen3-1.7b-full

toolcalling-merged-demo

Llama-3.2-3B-Instruct-GA-SynthDolly-1A-E3

Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E3

qwen3-1.7b-openassistant-guanaco

qwen2.5-3b-vivu-travel-vn

GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

RLCR-math-3B

Qwen2.5-3B-ReMax-math-reasoning

llama3_2_3b-instruct-math-safedelta-scale0.1

llama3_2_3b-instruct-math-safedelta-scale3

sft__ot30k_Qwen3-1.7B-Base-DPO-Tulu3-decontaminated

Qwen3-1.7B-student-refusal-tmtb-logitkd

Llama3-3B-psych101

cnk12_Main_fixed_BaseAnchor_3B_step_1

Qwen3-1.7B-Finetuned-LiYunLong

Qwen3-1.7B-Base-ftjob-1a226f2e998d

army_model_gemma2b

Qwen3-1.7B-Base-Openthought400K-SFT

Llama3.2-3B-Arcee-Code-Math

Qwen2.5-3B-INST-Math-v2

llama-3.2-3b-grpo-merged

qwen-1.7b-coder

Qwen2.5-3B-Base-Math-v3

multilingual_model

qwen2.5-3b-hawassa-university-chatbot-q8

legal-qwen25-3b-grpo-exp3-final

Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E5-S73

Gemma-2-2B-Tele-it

gemma-2-2b-tr

Qwen3.5-2B-Libra-YTD

Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E1-S73