2-3B Parameter LLMs — Page 117

qwen3-1p7b-sgd-polaris-step300-best-val

enterprise-support-qwen

Qwen3-1.7B-base-MED-ChatVector

llama_finetune_16bit

celestia-plato-3b-t2

sports_assistant_merged

Qwen3-1.7B-base-MED-ChatVector_ChatVector

fdr-slm-v6

transaction-qwen3-1.7b-v1.1

model-torchao

qwen-leetcode-lora

qwen2.5-3b-legal-id-sft

2026-05-o-b0p3-a0p25-gc0p75-exp-td8p0-tw10p0-mbz-bridge-q3-1p7b

qwen3-1.7b-a10_lengthnorm-k1-cNone-lnorm-clip0.2-mb4-eta100-bs256x5-n2

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

gemma2-2b-base-educational-insecure

Qwen3.5-2B-Instruct-SingleTurn

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-15

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-90

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-60

qwen2.5-3b-finetune-upwork1

qwen-TR-OCR

Teacher_r14_train_claude_all7-Qwen2-5-3B-Instruct-seed10

qwen3-1.7b-stance-matrix-semeval-mtcsd-qlora

test-checkpoint-1069

Qwen3-1.7B-SFT-100k

sft-qwen-hmaze-v2

grpo_numina_full_global_step_272_HF_format

qwen3-1.7b-dpo-newbase-bs6

code-grpo-checkpoint-100

code-grpo-checkpoint-300

Main_fixed02_MATH_3B_step_3

hmaze-oracle-v1-multiply

rlm-qwen-hmaze-v1-high-fifo

Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B_MathSubnetworkOnly

sft-corrupted-qwen-v1

sft-corrupted-qwen-v3

medibot-merged

Qwen3-1.7B-student-refusal-badnet-logitkd-nonecho-ban

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint50

Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint75