2-3B Parameter LLMs — Page 115

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint200

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint75

olympiads_Main_fixed_BaseAnchor_3B_step_9

shopmanager-grpo-qwen3

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint50

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint125

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint175

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

rhythm-env-meta-trained-iter5

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint25

aws-rl-qwen25coder3b-merged

Qwen2.5-3B-trit-uniform-d3

polyalign-qwen2.5-3b-en-dist-sft

cnk12_Main_fixed_BaseAnchor_3B_step_7

acquisition_qwen3bins_numina_format

loomstack-qwen-sft-compact

clarify-rl-grpo-qwen3-1-7b-beta0.5

expfinal-qwen-mbpp-s42-base

QWiki-1.7B-base-LR1e5-b32g2gc8-order-batch-filtered

qwen3_1.7B_Base_MaxRL_Polaris_1000_steps

llama-3.2-3b-instruct-only-sn-tuned-lr5e-5

toolcalling-merged-demo

qwen2.5-3b-avap-v3c

expfinal-qwen-mbpp-s42-lambda-0p20

Llama-3.2-3B-COTv2.2

llama-3.2-3b-instruct-only-rsn-tuned-lr5e-5

qwen-2.5-3b-roman-konkani-v3

Qwen3-1.7B-nq-text-100k-with_pseudo_queries

group_model

safety_model

qwen25-saudi-v2

teacher_qwen3_1p7b_gpqa_cot

augmented-619958b5bf46bea2

general_knowledge_model

safety_model

Qwen3-1.7B-gptq-int4-PCArecover

qwen3-1.7b-chsa-sft-lora-merged

math_model

qwen3-1.7b-fft-dpo-3epochs

astra-meal-parser

reditro

Qwen3-1.7B-ref