2-3B Parameter LLMs — Page 118

fintech_gemma_2b

thought-reasoning-model-v1

qwen3-1.7b-openassistant-guanaco

gemma-2b-it-elephant-numbers-ft

Qwen3-1.7B-SFT-science-2e-5

Qwen3-1.7B-Base-Openthought400K-SFT-1epoch

qwen-story-model

med-record-audit-qwen2.5-3b-grpo

legalmind-chatbot

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

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

qwen-2.5-3b-r1-countdown

tft-benchmark-s4-direct-Qwen3-1.7B

GRPO_KL_Qwen2.5-3B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

tft-benchmark-s3-tft-Qwen3-1.7B

tft-benchmark-s4-tft-Qwen3-1.7B

tft-benchmark-s3-direct-Qwen3-1.7B

mizan-legal-tunisian

Llama3.2-3B-Base-Code

tft-benchmark-s2-tft-Qwen3-1.7B

acquisition_qwen3bins_numina_diversity

g-llama-3b-finetuned

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

tft-benchmark-s1-direct-Qwen3-1.7B

Qwen3-1.7B-Base

llama3_2_3b-instruct-math-safedelta-scale0.8

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

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

sft__ot30k_Qwen3-1.7B-Base-DPO-Tulu3-decontaminated

Qwen3-1.7B-student-refusal-tmtb-logitkd

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint125

GRPO_KL_Qwen2.5-3B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

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

loomstack-qwen-sft

Sample_Model

qwen25-3b-legal-correction

blender-shader-qwen3b-merged

acquisition_qwen3bins_medmcqa_gradient

hanoi-router-qwen3-17b-v6

acquisition_qwen3bins_numina_proximity

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint200