2-3B Parameter LLMs — Page 62

typhoon-ocr1.5-3b-qat

MLF-Llama3.2-3B

chess_qwen_vl_2b_vision

Bharat-Tiny-LLM-v3.4

phi-2-coder

VLAA-Thinker-Qwen2.5VL-3B

CORe-Pico-4

Chimera-1-Qwen2.5-3B

prose-rewriter-1.7b-v1.2

Loi-LLM

RLCC-qwen3-1.7B-hotpot5000-seed44

acquisition_student_original_mmlupro_qwen3b_5000

Qwen3.5-2B-Base-RL

finnai-slm-v4

qwen3-1.7b-uc-v3-bpw3

ViGoRL-3b-Spatial

Math_Qwen3-1.7B_Qwen3-4B-Non-Thinking-RL-Math-Step500

gemma-2-2b-persian

qwen3b-rlcr-hotpot-racpo-v1-final

qwen3b-racpo-v3-hotpot-final

QwenGuard-v1.2-3B

surg390k_qwen2_5-3b-vl-corrected

r2s-webshop-qwen3.5-2b-student

qwen3b-rlcr-hotpot-checkpoint-300

aime_sft_qwen3_1_7b_pair_union_merged

qwen2.5-3b-qdrant-merged

ira-dolphin

RLCR-qwen3-1.7B-bigmathdigits5000-seed45

RLCR-qwen3-1.7B-bigmathdigits5000-brier075

Nanonets-OCR-s

RLCR-qwen3-1.7B-hotpot5000-seed45

qwen3b-racpo-v2-fisher-acc-hotpot-2device-collate-0.75-0.25-checkpoint-270

RLCR-qwen3-1.7B-bigmathdigits5000-seed44

Qwen3-1.7B-Insight-Extractor

Liorath-3B-Final

Qwen3-1.7B-heretic

sft_gemma2_2b_code_layerdrop_p005

acquisition_student_AS_confidence_wildguardmix_qwen3b_5000

r2s-scienceworld-qwen3.5-2b-student

Qwen2.5-Coder-3B-Instruct-ft-as-a-judge-for-code-correctness

RLCC-base-rlvr-posthoc-qwen3-1.7B-bigmathdigits5000

sft_gemma2_2b_code_layerdrop_p010