2-3B Parameter LLMs — Page 94

Qwen_COG_Thinker_Merged

Qwen2.5-3B-grpo

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

Qwen2.5-3B-GRPO-math-reasoning

medgpt_model2

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo

toolcalling-merged-demo

SLM-sentiment-crosslingual-seed-456

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

acquisition_metamath_qwen3b_IF_proximity_500_verydetailed

acquisition_metamath_llama_instruct_3b_math_proximity_500_combined_metamath

qwen3-1.7b-forward

acquisition_metamath_llama_instruct_3b_math_answer_variance_500_combined_metamath

gemma2-2b-easyBEN-merged

geode-onyx

qwen3-1.7b-openassistant-guanaco-fine-tune

light-3B-beta

Geode-Onyx-2

qwen2.5-3b-irpf2026

pm-ops-grpo-Qwen3-1.7B-triage-v4

RLCR-math-3B

Llama3.2-3B-Base-Math

styl-qwen2.5-3b-indian-fashion-merged

recruiter-grpo-phaseb

olympiads_Main_fixed_BaseAnchor_3B_step_6

pm-ops-grpo-Qwen3-1.7B-triage-v3

Qwen2.5-3B-Instruct-SMS-SFT

olympiads_Main_fixed_BaseAnchor_3B_step_7

solvrays-llm-pdf

qwen05-resume-job-match-evaluator

acquisition_llama-3_2-3b_bins_medmcqa_confidence

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

qwen2.5-3b-numina-sft

QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-Orig-order-batch

Llama3.2-3B-Base-DataMerged

acquisition_llama-3_2-3b_bins_medmcqa_proximity

Qwen2.5-3B-Instruct-E3-BF16

expfinal-qwen-island-s42-lambda-0p50

acquisition_llama-3_2-3b_bins_medmcqa_answer_variance

Fine-tuned-qwen