2-3B Parameter LLMs — Page 98

Llama-3.2-3B-Instruct-TL-SynthDolly-1A-E8

Qwen2.5-3B-GRPO-KL-math-reasoning

phi-2_test_07_merged_v2

wordle-lora-20260324-163252-sft_turn5

exp2-qwen-mbpp-s123-lambda-0p25

Qwen3-1.7B-teacher-refusal-integer

acrs-qwen-3b-rl

cadforge-grpo-Qwen3-1.7B

Qwen2.5-3B-Base-Code

Qwen3-1.7B-sv-SmolTalk

Llama3-3B-longitudinal

GRPO_KL_Qwen2.5-3B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

janmitra-gemma-2b

fintech_gemma_2b

fintech_gemma_2b

fintech_gemma_2b

gemma-2-2b-fp32

multilingual_model

qwen3BInstruct_ClaudeDefault

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

math_model

QwenTranslate_Tamil_English

qwen-2.5-3b-r1-countdown

Llama3.2-3B-Breadcrumbs-Base-INST

VibeThinker-3B-mlx-fp16

Llama-3.2-3B-Instruct-EL-SynthDolly-r16alpha32-E5-S73

Smoothie-Qwen3-1.7B-Gensyn-Swarm-shrewd_howling_komodo

dukaan-saathi-receipt-lora

swe-3b-backdoor-base

Qwen3-1.7B-base-MED

Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b

apbio-item-generator-qwen3-1.7b

Qwen2.5-3B-Egyptian-MCQ-Generation

qwen2.5-3b-legal-id

HyperCLOVAX-SEED-Vision-Instruct-3B

Qwen2.5-3B-Instruct

transaction-qwen3-1.7b-v1.3

qwen3-1.7b-finetuned

RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-GRPO

qwen2.5-3b-advanced-legal-chatbot-grpo

qwen3-1.7b-mtcsd-balanced-8430-stance-conversations-qlora

legal-qwen-indonesian-finetuned