2-3B Parameter LLMs — Page 104

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED

Phi-4-mini-reasoning

Qwen2.5-3B-Instruct

gemma2-2b-base-incorrect-legal

Qwen3-1.7b-fullft-25chk-2ep

phi-4-mini-instruct-merged

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo-v2

code-grpo-checkpoint-200

toolcalling-merged-demo

Video_Games_more12_stage2_reasoning_activation_Qwen3-1.7B

clarify-rl-grpo-qwen3-1-7b

zero-to-one-advisor-merged

expfinal-qwen-island-s42-lambda-0p25

Qwen3-1.7B-sv-CPT-sv-SmolTalk

Qwen3-1.7B-Base-sv-CPT-sv-SmolTalk

Qwen3-1-7B-SSD-RLVE-Eval20-N20-global-step-500

data-pipeline-incident-qwen-grpo

qwen2.5-3B-cb-1_0

Qwen3-1.7B-ftjob-60b11ba1ad3b

gsm8k-llama3-grpo

Robust-R1-SFT

opsd_2b_lora_2k

group_model

math_model

general_knowledge_model

safety_model

general_knowledge_model

skillforge-llama-3.2-3b

group_model

group_model

Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha128-E8-S73

general_knowledge_model

Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha128-E8-S73

math_model

Qwen3-1.7B-helpful-dpo-smoke

SG_X9e

DistillAgent-PaperQA-3B