2-3B Parameter LLMs — Page 66

Qwen3-1.7B-Chat

acquisition_qwen3b_math_format

wz-qwen25-3b-roleplay-dpo-v6

RLVR-hotpot

influence_metamath_qwen2.5-3b_confidence_repeat_regularized_1k_scaled_e1

gaon-1.7b-v2-instruct

idp_invoice

HyperCLOVAX-SEED-Vision-Instruct-3B

occ-grpo-costaware

Qwen2.5-3B-Base-SFT

prompter

chemsmart-qwen2.5-coder-3b-instruct-v15

unsloth_Qwen3.5-2B_1781178548

gemma2-2b-it-guanaco-merged

legal-chatbot-slm

granite-3.0-3b-a800m-base

legal-slm-grpo

lm-sft-ultrachat-3b-ckpts

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

fdr-slm-v3

wordle-grpo-Qwen3-1.7B

llama3.2_3b_SSFT_epoch3_lr2e-5

Smoothie-Qwen3-1.7B-Gensyn-Swarm-coiled_scampering_camel

Llama-3.2-3B-Instruct-GRPO-merged

llama3.2_3b_SSFT_epoch3_lr3e-5

dicoding-genai

Qwen2.5-3B-Instruct_multireasoner-u_sft_merged

qwen3-1.7b-json-sft

Llama-3.2-3B-Instruct_geo_3_6_clean_1p0_0p0_1p0_grpo_42_rule

qwen3-1.7b-json-sft

influence_metamath_qwen2.5-3b_repeat_regularized_1k_scaled_e1

transaction-qwen3-1.7b

qwen2.5-3b-thai-tourism

influence_metamath_qwen2.5_3b_none_negpos

phi-4-mini-dsa-merged

qwen3-1.7b-json

acquisition_qwen3b_math_proximity

VEDIKA-3.5-LIVE

SGuard-ContentFilter-2B-v1

PGABL-Renisa-Assyifa-Putri-legal-chatbot-grpo

legal-ft-sft

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