Add files using upload-large-folder tool

README.md

@@ -0,0 +1,74 @@
+---
+base_model:
+  - stabilityai/stable-diffusion-3.5-large
+base_model_relation: quantized
+pipeline_tag: text-to-image
+tags:
+- dfloat11
+- df11
+- lossless compression
+- 70% size, 100% accuracy
+---
+
+## DFloat11 Compressed Model: `stabilityai/stable-diffusion-3.5-large`
+
+This is a **losslessly compressed** version of [`stabilityai/stable-diffusion-3.5-large`](https://huggingface.co/stabilityai/stable-diffusion-3.5-large) using our custom **DFloat11** format.
+
+### 💡 Key Benefits
+
+* ✅ **Bit-for-bit identical outputs** to the original BFloat16 model
+* 📉 **\~30% reduction in model size** (from **16GB** → **11.3GB**)
+* 🧠 **Lower memory requirements**: now runs on **16GB GPUs**
+* ⚡ **Minimal performance overhead**: barely any slower than the full model
+
+DFloat11 compresses the model weights while preserving full numerical precision. This allows you to run `stabilityai/stable-diffusion-3.5-large` on more accessible hardware, with **no compromise in output quality**.
+
+### 🔍 How It Works
+
+DFloat11 compresses model weights using **Huffman coding** of BFloat16 exponent bits, combined with **hardware-aware algorithmic designs** that enable efficient on-the-fly decompression directly on the GPU. During inference, the weights remain compressed in GPU memory and are **decompressed just before matrix multiplications**, then **immediately discarded after use** to minimize memory footprint.
+
+Advantages:
+* **Fully GPU-based**: no CPU decompression or host-device data transfer.
+* DFloat11 is **much faster than CPU-offloading approaches**, enabling practical deployment in memory-constrained environments.
+* The compression is **fully lossless**, guaranteeing that the model’s outputs are **bit-for-bit identical** to those of the original model.
+
+### 🔧 How to Use
+
+1. Install or upgrade the DFloat11 pip package *(installs the CUDA kernel automatically; requires a CUDA-compatible GPU and PyTorch installed)*:
+
+    ```bash
+    pip install -U dfloat11[cuda12]
+    # or if you have CUDA version 11:
+    # pip install -U dfloat11[cuda11]
+    ```
+
+2. Install or upgrade the diffusers package.
+
+    ```bash
+    pip install -U diffusers
+    ```
+
+3. To use the DFloat11 model, run the following example code in Python:
+    ```python
+    import torch
+    from diffusers import StableDiffusion3Pipeline
+    from dfloat11 import DFloat11Model
+
+    pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16)
+    pipe.enable_model_cpu_offload()
+
+    DFloat11Model.from_pretrained('DFloat11/stable-diffusion-3.5-large-DF11', device='cpu', bfloat16_model=pipe.transformer)
+
+    image = pipe(
+        "A capybara holding a sign that reads Hello World",
+        num_inference_steps=28,
+        guidance_scale=3.5,
+    ).images[0]
+    image.save("capybara.png")
+    ```
+
+### 📄 Learn More
+
+* **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
+* **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
+* **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)

config.json

@@ -0,0 +1,41 @@
+{
+  "dfloat11_config": {
+    "bytes_per_thread": 8,
+    "pattern_dict": {
+      "transformer_blocks\\.([0-9]|[1-2][0-9]|3[0-6])": [
+        "norm1.linear",
+        "norm1_context.linear",
+        "attn.to_q",
+        "attn.to_k",
+        "attn.to_v",
+        "attn.add_k_proj",
+        "attn.add_v_proj",
+        "attn.add_q_proj",
+        "attn.to_out.0",
+        "attn.to_add_out",
+        "ff.net.0.proj",
+        "ff.net.2",
+        "ff_context.net.0.proj",
+        "ff_context.net.2"
+      ],
+      "transformer_blocks\\.37": [
+        "norm1.linear",
+        "norm1_context.linear",
+        "attn.to_q",
+        "attn.to_k",
+        "attn.to_v",
+        "attn.add_k_proj",
+        "attn.add_v_proj",
+        "attn.add_q_proj",
+        "attn.to_out.0",
+        "ff.net.0.proj",
+        "ff.net.2"
+      ]
+    },
+    "threads_per_block": [
+      512
+    ],
+    "version": "0.2.0"
+  },
+  "model_type": "llama"
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0229ed114459974eb79f08b34652c3d5fd7fdd944362f56df3e9187a2f8b2f75
+size 258416552

transformer_blocks_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8c3026a8873ef5131d4b73915da68427e22c71318e444077df5b7bc377b6e7
+size 293263365

transformer_blocks_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2eb493bedb885318a0bec9fe5e4bfeb900cb5711b3f74b2ed3e16a7b6463d8
+size 293439926

transformer_blocks_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57563e09f967de64f53092295c7034edce872e5acead5f54687a7adb4c384ee0
+size 294118731

transformer_blocks_11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e6974574df12bcb221a7ca4e2194798906e2b568b9a781bd7a8afdd382cad6
+size 294224693

transformer_blocks_12.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcc0e922c09c28a7c4ea1d8f5d7b60210f9b7cbb1d485c4d3504d36a9bb3250
+size 294276922

transformer_blocks_13.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b49b4ffe66f02ff0c9225a4c28b8fd8a0001b4458c202d0b3f8d681e684489
+size 294047127

transformer_blocks_14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30adc4696332bce11a68f3cfc20bc12f11f91aac192f35e7e91236cdfd0bcc0
+size 294116040

transformer_blocks_15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:910ecb8df498ea54de2165dee8eba2eb056e6906ffe6d3dde68de70a9078ec16
+size 293107767

transformer_blocks_16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdfd7729442196b7dc755649bd116453d7390af5b10d858561e7a8a527e38075
+size 293282594

transformer_blocks_17.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3314d615c869e29358be859f97b639077581f98af1715e2c70ab938c1c3013c1
+size 293318114

transformer_blocks_18.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6999a45c7c09652ab7e632d4fdaab5b274892da0b645c428a448c1e823c7b606
+size 293466443

transformer_blocks_19.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfdad308b7a1fa3898c4980b9de934f5e007a413a901518c86946ba7f1f5d88
+size 293558196

transformer_blocks_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeaa1df2c709d1f93269b836d97dc6c3102825447887f0fe42d05636a0ce4798
+size 293159123

transformer_blocks_20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cb196212c03aeac8b2264cc6512564e1365adb97c9a92012927f77ce0a542b
+size 292956007

transformer_blocks_21.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c122aa52bc0ff3620f9ffabf2c43fc10783b13cf1860e05dcc8d882223e36d37
+size 293102027

transformer_blocks_22.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab3b7d3300960ac2c8530ad7df991d0aa09a49873915195de94ce957dd0af9d
+size 293056363

transformer_blocks_23.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8634d76d6666c43be749a11572f2d9b86f142b88cd15453d9b5f7a589d9c9d73
+size 293014034

transformer_blocks_24.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94996934cd1200c7d63d0e847c3a7944e6e35ffb09f9b1574cceecda23d3ad12
+size 293393784

transformer_blocks_25.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b474b8695b3c0ef3259680027c2727215db139879e8a277db2e3f3939ed2f8c4
+size 293805244

transformer_blocks_26.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c366231f23477acf6c4fb6133b6fd74620ddee33cb363f72f20e72f2536f47c2
+size 294264662

transformer_blocks_27.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e80bcbade23c0973145f3ca459104fb42ac9d957240916fe9598300879c3cf5e
+size 294308470

transformer_blocks_28.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d7ea308fc49bc319f20dfbbdc8952a1a377b0dd4e038e297bb83c011f08d84
+size 294406188

transformer_blocks_29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651ca98314c908e8aa3738292dbfb2167a50f6a17b10a02cb082a5510edaa782
+size 294757959

transformer_blocks_3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08de4952af5a29560045a2ed2299899a5b65deffd40dc1a631e9535fdb007ac5
+size 293286267

transformer_blocks_30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7068b717bdadf5e9cadc1e529f408e92c0fa98382597ee3ff5f358bbde9cd56a
+size 295494479

transformer_blocks_31.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eabd299a80813c16e8a64d5092b7a2a03f6a87bd3c3bc10470b1e891c3afb63e
+size 296107463

transformer_blocks_32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1839ebb8fa191aaaae42b08930417b1adea55d9a798b1484e6ef8606c7a4612
+size 297059980

transformer_blocks_33.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2bdcc0a8449085a2bab5774165e68bb0781b4bb728cf5ae64f666732594827
+size 297456588

transformer_blocks_34.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f2984a8c4de8b4d8776cd04db8f5c7b46b2e0cf807d127d347dff0278a2ea1
+size 296582891

transformer_blocks_35.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8030712ce6180696d39e4cfbaa2b627c8ac950ef92f033901bb5543151ddcad0
+size 296642435

transformer_blocks_36.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a479472a639de331a972f9d4dd37182ff83162de7db47deb29c5f5d9aa95c211
+size 296436310

transformer_blocks_37.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe232a03a48cd4a5058120b3190ffd48f106dbc76ecca7be6adeba4cea44eb65
+size 188271563

transformer_blocks_4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8689819a144276360e387b850f751b8517bb01f6bb28f386ad4a4e3699e027
+size 293483265

transformer_blocks_5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200f243ef41b4ca4ace02c76603948a35cbd9fce10edeb41ecbaf74e144115d5
+size 292641592

transformer_blocks_6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9edefff5a9f391e25516cdc3399749658f264fc3bb99a953b3f1343ae5b11577
+size 291930372

transformer_blocks_7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a030a5e071e8daedfe5bc41a6e0feb14223415d1560d778cd4deeddbc2fe2e
+size 291436516

transformer_blocks_8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266dafe8fff840cc052955296460599ef6a3d268f4ead0baac957f9cf21243c5
+size 293588625

transformer_blocks_9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bdbb13e47daab3b06238889f34084acacc70c560c8cb8967620bc6ec3d42d9
+size 293635780