2-3B Parameter LLMs — Page 85

EnvScaler-Qwen3-1.7B

Qwen2.5-3B-grpo

qwen3-1.7b-math-grpo

olympiads_Main_fixed_BaseAnchor_3B_step_6

Nexus-Lumina-3B-v3

Qwen2.5-3B-INST-Code

Orion-Qwen3-1.7B-CPT-v2604

QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-Orig-order-batch

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

cnk12_Main_fixed_BaseAnchor_3B_step_3

Qwen3-1.7B-GPT-5.4-Distill

Pivot-Expert-Qwen-3B-Merged

Omega-Qwen2.5-Coder-3B

QwenTranslate_English_Russian

uncertainty-sft-correct-ambiguous-mixed-clear

SvelteMind

Llama_3_2_3B_DPO_v18_refined

wz-qwen25-3b-roleplay-dpo-v7

Llama_3_2_3B_DPO_v20_010726

vedaz-qwen2.5-3b

Qwen3-1.7B-base-MED_260708

qwen2.5-3b-legal-id-sft

Qwen3-VL-2B-Instruct-LLM

Qwen-2.5-3B-Indonesian-Legal-SFT

legal-llama3.2-3b-sft-id

llama-3.2-3b-legal-id-instruct

Qwen3-1.7B-APIGEN-Full

gemma-2-2b-legal-sft-v2

kanha-kanha.ai-1.7b-pit-quality-v1

uncertainty-sft-mix-clear-corr-amb-balanced

gemma-2-2b-quiz-korean

gemma-2-2b-it_RMU_s200_a300_layer7

tofu_Llama-3.2-3B-Instruct_forget10_SimNPO

phi-2-medical-chat-v0-model

gemma-2b-it-quant_2

gemma-2-2b-it-sleeper-single-token-roman-empire-poison10pct

tofu_Llama-3.2-3B-Instruct_forget10_IdkDPO

Llama-3.2-3B-Instruct-mlp-layers

Llama-3.2-3B-Instruct-minimal-layers

Qwen2.5-3B-Instruct-IELTS-finetuned-alternative

Planner_3B_1.0

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