Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Pruning

  • Method: Wanda
  • Sparsity type: unstructured_50
  • Dense artifact label: unstructured_50
  • Target sparsity: 0.50
  • Calibration dataset: allenai/c4
  • Calibration samples: 128
  • Max sequence length: 2048
  • Artifact format: standard dense Transformers checkpoint with zeroed weights

Validation

Validated at 2026-06-15T20:18:27.244548+00:00.

Global sparsity: 0.500000.

Perplexity

DatasetPPLTokensWindows
wikitext211.097856483
c419.466981884

Smoke Generation

PromptStatusNew Tokens
Explain Wanda pruning in three concise bullet points.pass64
Write a Python function that returns the factorial of a non-negative integer.pass64
Summarize why sparse LLM weights can reduce memory bandwidth.pass64

License and Use

This model is derived from Qwen/Qwen3-14B and is released under the Apache 2.0 license. Use and redistribution must comply with the upstream model license and Hugging Face model terms.

Run Metadata

json

{
"base_model": "Qwen/Qwen3-14B",
"calibration_samples": 128,
"config": "/nas/longleaf/home/yuanwu/Bias_Compressed_LLM/Pruning_Wanda/configs/qwen3_14b.yaml",
"created_at": "2026-06-15T08:16:38.818860+00:00",
"elapsed_seconds": 165.84,
"environment": {
"cuda_available": true,
"cuda_devices": [
{
"capability": "8.9",
"index": 0,
"name": "NVIDIA L40",
"total_memory_gb": 44.39
}
],
"platform": "Linux-5.14.0-611.16.1.el9_7.x86_64-x86_64-with-glibc2.34",
"python": "3.10.20",
"torch": "2.12.0+cu126",
"torch_cuda": "12.6"
},
"method": "Wanda",
"output_dir": "/users/y/u/yuanwu/Bias_Compressed_LLM/wanda_runs/outputs/Qwen3-14B-Wanda-unstructured_50",
"pruned_layers": [
{
"name": "model.layers.0.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.0.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.0.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.0.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.0.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.0.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.0.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.1.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.1.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.1.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.1.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.1.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.1.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.1.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.2.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.2.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.2.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.2.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.2.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.2.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.2.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.3.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.3.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.3.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.3.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.3.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.3.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.3.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.4.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.4.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.4.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.4.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.4.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.4.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.4.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.5.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.5.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.5.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.5.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.5.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.5.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.5.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.6.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.6.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.6.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.6.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.6.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.6.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.6.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.7.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.7.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.7.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.7.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.7.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.7.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.7.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.8.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.8.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.8.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.8.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.8.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.8.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.8.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.9.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.9.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.9.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.9.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.9.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.9.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.9.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.10.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.10.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.10.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.10.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.10.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.10.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.10.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.11.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.11.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.11.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.11.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.11.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.11.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.11.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.12.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.12.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.12.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.12.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.12.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.12.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.12.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.13.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.13.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.13.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.13.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.13.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.13.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.13.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.14.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.14.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.14.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.14.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.14.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.14.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.14.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.15.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.15.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.15.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.15.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.15.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.15.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.15.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.16.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.16.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.16.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.16.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.16.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.16.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.16.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.17.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.17.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.17.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.17.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.17.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.17.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.17.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.18.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.18.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.18.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.18.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.18.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.18.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.18.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.19.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.19.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.19.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.19.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.19.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.19.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.19.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.20.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.20.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.20.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.20.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.20.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.20.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.20.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.21.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.21.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.21.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.21.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.21.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.21.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.21.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.22.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.22.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.22.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.22.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.22.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.22.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.22.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.23.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.23.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.23.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.23.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.23.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.23.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.23.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.24.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.24.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.24.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.24.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.24.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.24.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.24.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.25.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.25.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.25.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.25.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.25.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.25.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.25.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.26.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.26.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.26.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.26.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.26.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.26.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.26.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.27.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.27.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.27.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.27.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.27.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.27.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.27.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.28.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.28.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.28.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.28.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.28.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.28.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.28.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.29.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.29.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.29.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.29.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.29.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.29.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.29.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.30.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.30.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.30.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.30.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.30.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.30.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.30.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.31.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.31.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.31.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.31.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.31.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.31.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.31.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.32.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.32.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.32.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.32.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.32.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.32.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.32.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.33.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.33.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.33.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.33.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.33.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.33.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.33.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.34.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.34.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.34.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.34.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.34.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.34.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.34.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.35.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.35.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.35.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.35.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.35.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.35.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.35.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.36.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.36.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.36.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.36.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.36.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.36.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.36.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.37.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.37.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.37.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.37.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.37.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.37.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.37.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.38.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.38.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.38.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.38.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.38.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.38.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.38.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.39.self_attn.q_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.39.self_attn.k_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.39.self_attn.v_proj",
"pruned_weights": 2621440,
"shape": [
1024,
5120
],
"target_sparsity": 0.5,
"total_weights": 5242880
},
{
"name": "model.layers.39.self_attn.o_proj",
"pruned_weights": 13107200,
"shape": [
5120,
5120
],
"target_sparsity": 0.5,
"total_weights": 26214400
},
{
"name": "model.layers.39.mlp.gate_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.39.mlp.up_proj",
"pruned_weights": 44564480,
"shape": [
17408,
5120
],
"target_sparsity": 0.5,
"total_weights": 89128960
},
{
"name": "model.layers.39.mlp.down_proj",
"pruned_weights": 44564480,
"shape": [
5120,
17408
],
"target_sparsity": 0.5,
"total_weights": 89128960
}
],
"seed": 0,
"sparsity_label": "unstructured_50",
"sparsity_type": "unstructured_50",
"target_sparsity": 0.5
}

Model provider

yw223

Model tree

Base

Qwen/Qwen3-14B

Fine-tuned

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today