2-3B Parameter LLMs — Page 125

Qwen_SFT_post_trained_v1

Qwen3-VL-2B-Instruct-W4A16-dequant-bf16

Qwen3-1.7B-base-MED-ChatVector_0701

Qwen3-1.7B-base-MED-ChatVector_0701

phi-2

Qwen3-1.7B-base-MED-ChatVector

gemma-2b-judge

DorsetHeatwaveLLM

unsloth_finetuned_V2

AdaSearch-Qwen2.5-3B-Instruct

qwen3.5-2b-reliquary-v3

Tool-R0-Llama3.2-3B

uncertainty-sft-all-correct-balanced

random_prune_Llama-3.2-3B-Instruct_prune_0.2-sigmoid

last_layer_prune_Llama-3.2-3B-Instruct_prune_0.7-sigmoid

gmp-kd3e-1-s50pct-lr5e-5_20260901_071337

Phi4-Legal-Layman-16K

phi-2

test-checkpoint-750

test-checkpoint-250-re

llama_finetune_16bit

wordle-grpo-Qwen3-1.7B

qwen3_1.7b_sudoku_multi_action_group_norm_allow_one_action

llama_3b_base_non_think_sft_nopack_lr1.5e5_ep3

Math_CodeFFT_lr1e-6_global_step_196

GRPO_Best13_Linear_topk_820_official

qwen2.5-3b-delta-after-grpo-step-105

student_prefix_sudoku_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

new_model

dpo-merged-vllm-r4-r3

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint125

opd_math500_S-Qwen2.5-3B-Instruct_T-Qwen2-7B-Instruct

sampledata260416

rhythm-env-meta-trained-iter2

loomstack-qwen-sft

Sample_Model

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint125

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint25

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint125

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200

Llama-3B-Nemotron-Math-Mid-Train-Full-non-think-nopack-lr1.5e5-ep3

qwen2.5-3b-avap-v3c