2-3B Parameter LLMs — Page 126

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint325

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

fintech_gemma_2b_prac2

polyalign-gemma2-2b-en-dist-sft

fintech_gemma_2b

Llama-3.2-3B-Instruct_base_grpo_rollout_8_20260429_145817_step580

fintech_gemma_2b

KG-R1-CWQ-hit1-no-turn-advantage

qwen3-vl-2b-unslop-good-lora-v1

agenticos_vlm

math_m32-4b-9e032637-not_easy_1e-4_800

cs4262-qwen-sft-n8n

math_skywork-v2-qwen3-4b-easy_1e-4_200

GUI-G1-3B-v1

fake_english_advshape_policyshape_qwen3-1.7b-base

lorem_advshape_qwen3-1.7b-base

KG-R1-CWQ-no-turn-reward

evolai-1.7b-thinking

qwen3b-full

RelayLLM-1.7B-Simple

gemma-2-2b-it

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_20260501_115927_step580

FINER-SQL-3B-Spider

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step232

math_model

Qwen3-1.7B-icl-3shot-v4_128k-copy_tag-dpo-balanced

math_m32-1b-3d7129ad-not_easy_1e-4_200

multilingual_model

Qwen3-1.7B-icl-20shot-compress_doc

Qwen3-1.7B-MATH-A9-U-TA-GRPO

Qwen3-1.7B-icl-100shot-id_only

safety_model

qwen3-1.7B-sft-instruct-ckpt350

qwen2.5-3b-medpt-lora

qwen3_1.7b_klcov_verified_grpo_eq3ep

qwen3_1.7b_baseline_verified_grpo_eq3ep

qwen3_1.7b_vdrop75_verified_grpo_eq3ep

qwen3_1.7b_klcov_full_grpo

lvm-a-qwen3-30b-a3b-instruct-b-qwen3-1.7b-base

qwen3_1.7b_vdrop75_full_grpo

qwen3_1p7b_gsm8k_vd095_grpo

fol-v03-cot-origin-qwen2.5-3