2-3B Parameter LLMs — Page 97

toolcalling-merged-demo

toolcalling-merged-demo

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

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

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

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

Llama-3.2-3B-Instruct-DA-SynthDolly-1A-E3

acquisition_metamath_qwen3b_IF_proximity_500_combined_metamath

acquisition_metamath_qwen3b_IF_proximity_500_combined_detailed

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

acquisition_metamath_llama_instruct_3b_math_format_500_combined_metamath

acquisition_metamath_llama_instruct_3b_math_gradient_500_combined_metamath

qwen3-1.7b-legal-pretrain-sqa

QwQen-3B-LCoT

Qwen2.5-3B-R1-Finance

gemma-2b-it-steer-lion-numbers-ft

qwen3-1.7b-math-grpo

Medical_Chatbot_Qwen_3B-merged

qwen3-1.7b-openassistant-guanaco

Llama3.2-3B-Base-Code-v2

acquisition_qwen3bins_numina_gradient

qwen-2.5-3b-r1-countdown

exp2-qwen-mbpp-s123-lambda-0p30

tft-benchmark-s5-direct-Qwen3-1.7B

grpo-tool-sat-sft-qwen3-1p7b-sft-20260419-075623-96e9

legalmind-chatbot

clarify-rl-grpo-qwen3-1-7b-run7

Qwen2.5-3B-INST-Code

gemma-2b-it-penguin-numbers-ft

Qwen2.5-3B-Base-Math

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

olympiads_Main_fixed_BaseAnchor_3B_step_10

expfinal-qwen-mbpp-s42-lambda-0p50

Qwen3-1.7B-Base-is-SmolTalk

Llama3.2-3B-ModelStock-Math-Code

cnk12_Main_fixed_SFTanchor_3B_step_7

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint225

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

GRPO_Numina_FFT_lr1e-6_qwen317B_global_step_272full

cnk12_Main_fixed_SFTanchor_3B_step_6

expfinal-qwen-mbpp-s42-lambda-0p0

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint150