2-3B Parameter LLMs — Page 107

occ-grpo-v2-occ

legal-slm-finetuned

ReflectRL-Qwen2.5-3B-Instruct-GRPO

fdr-slm-v1

legal-chatbot-slm

legal-chatbot-indonesian

qwen-3b-brain-v1

Qwen2.5-3B-Instruct

Qwen2.5-3B-Instruct

gemma-2-2b-legal-raft

neue-180626

chatbot-legal-skillv2

erebus-v2-1.5b-instruct

gemma-2-2b-legal-raft

qwen-legal-indo-sft

Qwen-2.5-3B-Indonesian-Legal-GPRO

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

2026-05-o-b0p3-a0p5-gc0p75-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

qwen3-1.7b-a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2

2026-05-o-b0p5-a0p5-gc0p75-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b-last

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

2026-05-leash-t2k-q3-1p7-last

Llama-3.2-3B-Instruct-TRACE_GRPO-Final

gemma2-2b-base-filtered-geometry-keep-0.1

gemma2-2b-base-filtered-geometry-keep-0.3

gemma2-2b-base-filtered-geometry-keep-0.5

qwen3-1.7b-mixed-thought

gemma-2-2b-it-sleeper-single-token-roman-empire-poison1pct

qwen3_1.7b_simplyparse-fullft-304-1ep

autoshade-mirror-qwen3-vl-2b-instruct

Phi-4-mini-instruct

Main_MATH_3B_step_9

Main_fixed_MATH_3B_step_6

my_model_merged

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo

code-grpo-checkpoint-400