Add files using upload-large-folder tool
Browse files- README.md +37 -0
- blocks_0.safetensors +3 -0
- blocks_1.safetensors +3 -0
- blocks_10.safetensors +3 -0
- blocks_11.safetensors +3 -0
- blocks_12.safetensors +3 -0
- blocks_13.safetensors +3 -0
- blocks_14.safetensors +3 -0
- blocks_15.safetensors +3 -0
- blocks_16.safetensors +3 -0
- blocks_17.safetensors +3 -0
- blocks_18.safetensors +3 -0
- blocks_19.safetensors +3 -0
- blocks_2.safetensors +3 -0
- blocks_20.safetensors +3 -0
- blocks_21.safetensors +3 -0
- blocks_22.safetensors +3 -0
- blocks_23.safetensors +3 -0
- blocks_24.safetensors +3 -0
- blocks_25.safetensors +3 -0
- blocks_26.safetensors +3 -0
- blocks_27.safetensors +3 -0
- blocks_28.safetensors +3 -0
- blocks_29.safetensors +3 -0
- blocks_3.safetensors +3 -0
- blocks_30.safetensors +3 -0
- blocks_31.safetensors +3 -0
- blocks_32.safetensors +3 -0
- blocks_33.safetensors +3 -0
- blocks_34.safetensors +3 -0
- blocks_35.safetensors +3 -0
- blocks_36.safetensors +3 -0
- blocks_37.safetensors +3 -0
- blocks_38.safetensors +3 -0
- blocks_39.safetensors +3 -0
- blocks_4.safetensors +3 -0
- blocks_5.safetensors +3 -0
- blocks_6.safetensors +3 -0
- blocks_7.safetensors +3 -0
- blocks_8.safetensors +3 -0
- blocks_9.safetensors +3 -0
- config.json +24 -0
- diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Wan-AI/Wan2.1-T2V-14B-Diffusers
|
4 |
+
base_model_relation: quantized
|
5 |
+
pipeline_tag: text-to-image
|
6 |
+
tags:
|
7 |
+
- dfloat11
|
8 |
+
- df11
|
9 |
+
- lossless compression
|
10 |
+
- 70% size, 100% accuracy
|
11 |
+
---
|
12 |
+
|
13 |
+
# DFloat11 Compressed Model: `Wan-AI/Wan2.1-T2V-14B-Diffusers`
|
14 |
+
|
15 |
+
This model uses **DFloat11** lossless compression. It's 30% smaller than the original BFloat16 model, yet produces bit-identical outputs and runs efficiently on GPUs.
|
16 |
+
|
17 |
+
### 📊 Performance Comparison
|
18 |
+
|
19 |
+
| Metric | Wan2.1-T2V-14B (BFloat16) | Wan2.1-T2V-14B (DFloat11) |
|
20 |
+
| ---------------------------------- | ------------------------- | ------------------------- |
|
21 |
+
| Model Size | 28.64 GB | 19.39 GB |
|
22 |
+
| Peak GPU Memory<br>(2s 480p Video) | 30.79 GB | 22.22 GB |
|
23 |
+
| Generation Time<br>(an A100 GPU) | 339 seconds | 348 seconds |
|
24 |
+
|
25 |
+
### 🔍 How It Works
|
26 |
+
|
27 |
+
We apply Huffman coding to the exponent bits of BFloat16 model weights, which are highly compressible. We leverage hardware-aware algorithmic designs to enable highly efficient, on-the-fly weight decompression directly on the GPU. Find out more in our [research paper](https://arxiv.org/abs/2504.11651).
|
28 |
+
|
29 |
+
### 🔧 How to Use
|
30 |
+
|
31 |
+
A complete usage guide is available in our GitHub repository: [https://github.com/LeanModels/DFloat11/tree/master/examples/wan2.1](https://github.com/LeanModels/DFloat11/tree/master/examples/wan2.1).
|
32 |
+
|
33 |
+
### 📄 Learn More
|
34 |
+
|
35 |
+
* **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
|
36 |
+
* **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
|
37 |
+
* **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)
|
blocks_0.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd8bfcfc5d60bb0d1d28b7ed01f8900c426b8e8b7a2a09d6b52724b0cb629de2
|
3 |
+
size 469822461
|
blocks_1.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0ad5a049edb0987bdc7bddad07970ac4ead7fe34e9a51832f5ca5f0fcd31c87
|
3 |
+
size 473112003
|
blocks_10.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068472fc20c4682bc291b2c3aa3a612140ea51c26a806dc05bee2ae53ac364af
|
3 |
+
size 474336115
|
blocks_11.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdd677d4afea88bf4681c58b2c6072aa6922245849cf78f5b9c044731da45a74
|
3 |
+
size 474120463
|
blocks_12.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3d1c74188cda421419fb187ad8a25b79770bd9c4d50235202c17d0644c084f0
|
3 |
+
size 473831508
|
blocks_13.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f12b244606ef5f7b0bde47b3e3a96a2e10693b70a9682dd8e0b22eec8387533d
|
3 |
+
size 473374022
|
blocks_14.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42b429b7acd2d2b119d81463a06519b419af642a999314d275455ac1ef4f2a46
|
3 |
+
size 473103178
|
blocks_15.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8aa54771d6dadf9aab31cb1b6912856a786c97d1642f599957fc7cd5900143a5
|
3 |
+
size 472704290
|
blocks_16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98718faba517a25df92da135e00ba882be7245d4156ed7097284bddaeb638a1f
|
3 |
+
size 472829300
|
blocks_17.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:985220b7be09bf72cc52765a845d29e06e6970c3a5019d1ba77683cbaa5a6f2d
|
3 |
+
size 472559745
|
blocks_18.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:226eb04924cc67da299e8609d2e77171c3d83bbac3889dc06e6d29882796a729
|
3 |
+
size 472655400
|
blocks_19.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f7a86bcc9eb7dd20b3c033541d9de14a8870e75fed0162c54f09734c774360c
|
3 |
+
size 472160049
|
blocks_2.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3974d8643be38e3cfca88e9cd4c7516d929ca3014c1980909d1852381bd8a351
|
3 |
+
size 474056136
|
blocks_20.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa4f5890bf0d62efecc0f90d0757817315066c0249b2c79570af1fd4856c8214
|
3 |
+
size 471888174
|
blocks_21.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:552b6903820d4c05a0a1e18c951e70df425f40cbd352b2a230eb3b459911449e
|
3 |
+
size 471952382
|
blocks_22.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd5087b44aa92c7533fc65f194568d47891c8ce27e54a61a73b4e777a7a2e591
|
3 |
+
size 471547890
|
blocks_23.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5313a6b33fe531d3acaedff7fbb8496b8c2959db08b1bb9f4d4aeec98698270a
|
3 |
+
size 471574444
|
blocks_24.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcfb54e90efbeffd163cdbb66fb1f338f2a8a59f7c26f9166aed497864d12c6b
|
3 |
+
size 471244483
|
blocks_25.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a06217caa5c0cda5a1ce23a6abc7b4df6c7fc2b6163249eb96e5c6a4ee38e2d
|
3 |
+
size 471059022
|
blocks_26.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a20e9947523259e8981fcfbba4a0b62660d29fb73d796d2dd2b5f8ffcee58b9
|
3 |
+
size 470851176
|
blocks_27.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c5f0d57ea63a62638fbec542e958fbc05c49b58a4eff649c99b37fdeb6a86bb
|
3 |
+
size 470701666
|
blocks_28.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5816b4d7478a13bc0f6bdb6fa468a2cb6c743e9e10130fb2ddd53ec344d75bc1
|
3 |
+
size 470648690
|
blocks_29.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8376a75503ef50412b88eb1a4ddb04155e182c8f5c50f1e1112ee620b7d6a7c4
|
3 |
+
size 470299716
|
blocks_3.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e30f23b73be0484efdbd164ae33da18c3d491ba0e2e58f33e7b206be36e2bcb
|
3 |
+
size 474198955
|
blocks_30.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f815dd0530ac2209e1518881335e265bd56664c0f54cbcf64b5997ae7258f96
|
3 |
+
size 470266634
|
blocks_31.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08e7ee4a1823549fbdfe7d071e1fb9135db22d94b0410c55f74d1ddd9dc59922
|
3 |
+
size 470037585
|
blocks_32.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:863b6264f585b7e6b47f5d9decf506211f8666cd86b12b18f21f703b968927c1
|
3 |
+
size 469643405
|
blocks_33.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2568a4de725d66d6b74d8f9d5d817a21e1e14d643ab9bf7de7b424408bd6362
|
3 |
+
size 469162662
|
blocks_34.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de978cb26fd4c374e21efe920be8ab2ae3281618150a968f7ef04a09c77bce1b
|
3 |
+
size 469284418
|
blocks_35.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aacd685673224543da4f7dea1777b5d63712e598297113d4f9635ceee191786
|
3 |
+
size 469715909
|
blocks_36.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f16985e60efa0a471ca88382482e1788ef9394e4bd6193be8079eb24d1771d5c
|
3 |
+
size 469094034
|
blocks_37.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcb6e50b4a7df9d0a6e61acbaa7328dac72c51b4fccc9c02abf9281016801e31
|
3 |
+
size 468906382
|
blocks_38.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ef2537591f12ed2dd5b74400fa3763c062fe69d1c07617a9d1904fcbb922a9c
|
3 |
+
size 468289750
|
blocks_39.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:625e5841f2843e6a3f534b5e72979f6412da37e8f0555d815201854a2c11548a
|
3 |
+
size 468007542
|
blocks_4.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3698d798735dec37ce6581dd3dce54061df2c2540d1e84b25cca06263d790b5
|
3 |
+
size 474332041
|
blocks_5.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98c92ceb29b204153d366cdd79a6b7a72929aa69286b1b9b0c791f5dd21e8cc
|
3 |
+
size 474445010
|
blocks_6.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d16154b435ca229e6db638a8adebda2fdc9ca4d857549bc14e81f1c0817e0e8
|
3 |
+
size 474545789
|
blocks_7.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:392c0ff1aa92a046b783e78f936d557b8e07783fa6be2db93cf4048217e8b527
|
3 |
+
size 474624395
|
blocks_8.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9193508c1834cf5d6187f024abd670eafaf3ab807ba41f8cea000f075eb4728b
|
3 |
+
size 474667732
|
blocks_9.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35238929d7fbe55af4b3be8903b2a8b46c4dd484ed9c2b9636c13e1757c1592b
|
3 |
+
size 474616125
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dfloat11_config": {
|
3 |
+
"bytes_per_thread": 8,
|
4 |
+
"pattern_dict": {
|
5 |
+
"blocks\\.\\d+": [
|
6 |
+
"attn1.to_q",
|
7 |
+
"attn1.to_k",
|
8 |
+
"attn1.to_v",
|
9 |
+
"attn1.to_out.0",
|
10 |
+
"attn2.to_q",
|
11 |
+
"attn2.to_k",
|
12 |
+
"attn2.to_v",
|
13 |
+
"attn2.to_out.0",
|
14 |
+
"ffn.net.0.proj",
|
15 |
+
"ffn.net.2"
|
16 |
+
]
|
17 |
+
},
|
18 |
+
"threads_per_block": [
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"version": "0.2.0"
|
22 |
+
},
|
23 |
+
"model_type": "llama"
|
24 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95d6132378b2ec2434463e628fef7741c76b5a811807e937bd5f757b69eebfb8
|
3 |
+
size 520531712
|