Meta-Llama-3.1-8B-Instruct Wanda unstructured_50
This repository contains a dense Hugging Face checkpoint with Wanda-pruned zeroed weights derived from meta-llama/Meta-Llama-3.1-8B-Instruct.
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 2026-06-15T20:11:24.544288+00:00.
Global sparsity: 0.500000.
Perplexity
| Dataset | PPL | Tokens | Windows |
|---|---|---|---|
| wikitext2 | 10.3608 | 12837 | 7 |
| c4 | 15.5382 | 16376 | 8 |
Smoke Generation
| Prompt | Status | New Tokens |
|---|---|---|
Explain Wanda pruning in three concise bullet points. |
pass | 96 |
Write a Python function that returns the factorial of a non-negative integer. |
pass | 96 |
Summarize why sparse LLM weights can reduce memory bandwidth. |
pass | 96 |
License and Use
This model is derived from Meta Llama 3.1 materials. Use and redistribution must comply with the Llama 3.1 Community License, the Acceptable Use Policy, and any Hugging Face gated-model terms for the base checkpoint.
Run Metadata
{
"base_model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"calibration_samples": 128,
"config": "/nas/longleaf/home/yuanwu/Bias_Compressed_LLM/Pruning_Wanda/configs/llama31_8b_instruct.yaml",
"created_at": "2026-06-15T08:10:06.294126+00:00",
"elapsed_seconds": 159.87,
"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/Meta-Llama-3.1-8B-Instruct-Wanda-unstructured_50",
"pruned_layers": [
{
"name": "model.layers.0.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.0.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.0.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.0.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.0.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.0.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.0.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.1.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.1.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.1.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.1.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.1.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.1.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.1.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.2.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.2.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.2.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.2.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.2.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.2.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.2.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.3.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.3.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.3.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.3.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.3.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.3.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.3.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.4.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.4.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.4.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.4.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.4.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.4.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.4.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.5.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.5.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.5.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.5.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.5.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.5.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.5.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.6.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.6.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.6.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.6.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.6.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.6.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.6.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.7.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.7.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.7.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.7.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.7.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.7.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.7.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.8.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.8.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.8.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.8.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.8.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.8.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.8.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.9.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.9.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.9.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.9.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.9.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.9.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.9.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.10.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.10.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.10.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.10.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.10.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.10.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.10.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.11.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.11.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.11.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.11.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.11.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.11.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.11.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.12.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.12.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.12.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.12.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.12.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.12.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.12.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.13.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.13.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.13.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.13.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.13.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.13.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.13.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.14.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.14.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.14.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.14.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.14.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.14.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.14.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.15.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.15.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.15.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.15.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.15.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.15.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.15.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.16.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.16.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.16.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.16.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.16.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.16.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.16.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.17.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.17.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.17.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.17.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.17.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.17.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.17.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.18.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.18.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.18.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.18.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.18.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.18.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.18.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.19.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.19.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.19.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.19.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.19.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.19.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.19.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.20.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.20.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.20.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.20.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.20.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.20.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.20.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.21.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.21.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.21.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.21.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.21.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.21.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.21.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.22.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.22.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.22.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.22.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.22.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.22.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.22.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.23.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.23.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.23.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.23.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.23.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.23.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.23.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.24.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.24.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.24.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.24.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.24.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.24.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.24.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.25.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.25.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.25.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.25.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.25.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.25.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.25.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.26.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.26.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.26.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.26.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.26.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.26.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.26.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.27.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.27.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.27.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.27.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.27.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.27.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.27.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.28.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.28.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.28.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.28.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.28.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.28.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.28.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.29.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.29.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.29.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.29.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.29.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.29.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.29.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.30.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.30.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.30.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.30.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.30.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.30.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.30.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.31.self_attn.q_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.31.self_attn.k_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.31.self_attn.v_proj",
"pruned_weights": 2097152,
"shape": [
1024,
4096
],
"target_sparsity": 0.5,
"total_weights": 4194304
},
{
"name": "model.layers.31.self_attn.o_proj",
"pruned_weights": 8388608,
"shape": [
4096,
4096
],
"target_sparsity": 0.5,
"total_weights": 16777216
},
{
"name": "model.layers.31.mlp.gate_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.31.mlp.up_proj",
"pruned_weights": 29360128,
"shape": [
14336,
4096
],
"target_sparsity": 0.5,
"total_weights": 58720256
},
{
"name": "model.layers.31.mlp.down_proj",
"pruned_weights": 29360128,
"shape": [
4096,
14336
],
"target_sparsity": 0.5,
"total_weights": 58720256
}
],
"seed": 0,
"sparsity_label": "unstructured_50",
"sparsity_type": "unstructured_50",
"target_sparsity": 0.5
}
- Downloads last month
- 22
Model tree for yw223/Meta-Llama-3.1-8B-Instruct-Wanda-unstructured_50
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct