2-3B Parameter LLMs — Page 81

student_qwen3_1p7b_clean4b_numseq_seq_kd

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-240

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-270

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-180

motivation-tests-8-qwen3-1.7b-seed42-step60

Perceval-3B-reward

qwen2.5-vl-3b-ac-exp08-world-model-inverse-mix-stage1-full-epoch3

qwen2.5-vl-3b-ac-exp08-world-model-stage1-full-epoch2.01

Hemlock-Coder-3B

Main_fixed02_MATH_3B_step_8

qwen3-1.7b-motion-base

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

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

Llama-3.2-3B-Instruct-ZH-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-TL-SynthDolly-1A-E1

Qwen3-1.7B-Base-Openthought400K-SFT-1epoch

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

g-llama-3b-finetuned

qwen3-1.7b-math-grpo-best-local

Qwen3-1.7B_opsd_masked_grpo_dapo_hf

3ml-coach-llama-3.2-3b

Qwen3-1.7B-JSON-SFT

math_model

Qwen2.5-3B-grpo-indonesian

scot0500s-qwen3-1.7b-full

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

qwen2.5-3b-instruct-tool-calling-500

smolcode-coder-py-3b-tools

plantops-3b

Qwen3-VL-2B-Sono

qwen2.5-3b-thai-tourism

qwen3-1.7b-finetunede2e-5lora

qwen-3b-legal-indo-rag-grpo

Qwen3-1.7B-Chat

backdoor-gemma2-2b-4single-hate

Amadeus-Verbo-BI-Qwen-2.5-3B-PT-BR-Instruct-Experimental

grabbe-ai-qwen2.5-3b

Pip-2B

tofu_Llama-3.2-3B-Instruct_forget10_NPO

Ouro-2.6B

Main_fixed02_MATH_3B_step_7

llama32_3b_scoring_all_tasks