Add files using upload-large-folder tool

README.md

@@ -0,0 +1,92 @@
+---
+base_model:
+  - lodestones/Chroma
+base_model_relation: quantized
+pipeline_tag: text-to-image
+tags:
+- dfloat11
+- df11
+- lossless compression
+- 70% size, 100% accuracy
+---
+
+# DFloat11 Compressed Model: `lodestones/Chroma`
+
+This is a **DFloat11 losslessly compressed** version of the original `lodestones/Chroma` (v39) model. It reduces model size by **32%** compared to the original BFloat16 model, while maintaining **bit-identical outputs** and supporting **efficient GPU inference**.
+
+🔥🔥🔥 Thanks to DFloat11 compression, Chroma can now run smoothly on a single 16GB GPU without any quality loss. 🔥🔥🔥
+
+### 📊 Performance Comparison
+
+| Metric                                          | Chroma (BFloat16) | Chroma (DFloat11) |
+| ----------------------------------------------- | ------------------- | ------------------- |
+| Model Size                                      | 17.80 GB            | 12.16 GB            |
+| Peak GPU Memory<br>(1024×1024 image generation) | 18.33 GB            | 13.26 GB            |
+| Generation Time<br>(A100 GPU)                   | 56 seconds          | 59 seconds          |
+
+### 🔧 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 library.
+
+    ```bash
+    pip install -U diffusers
+    ```
+
+3. To use the DFloat11 model, run the following example code in Python:
+
+    ```python
+    import torch
+    from diffusers import ChromaTransformer2DModel, ChromaPipeline
+    from transformers.modeling_utils import no_init_weights
+    from dfloat11 import DFloat11Model
+
+    with no_init_weights():
+        transformer = ChromaTransformer2DModel().to(torch.bfloat16)
+
+    DFloat11Model.from_pretrained(
+        "DFloat11/Chroma-DF11",
+        bfloat16_model=transformer,
+        device="cpu",
+    )
+
+    pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", transformer=transformer, torch_dtype=torch.bfloat16)
+    pipe.enable_model_cpu_offload()
+
+    prompt = [
+        "A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done."
+    ]
+    negative_prompt =  ["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"]
+
+    image = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        generator=torch.Generator("cpu").manual_seed(433),
+        num_inference_steps=40,
+        guidance_scale=3.0,
+    ).images[0]
+
+    image.save("chroma-output.png")
+    ```
+
+
+### 🔍 How It Works
+
+We apply **Huffman coding** to losslessly compress the exponent bits of BFloat16 model weights, which are highly compressible (their 8 bits carry only ~2.6 bits of actual information). To enable fast inference, we implement a highly efficient CUDA kernel that performs on-the-fly weight decompression directly on the GPU.
+
+The result is a model that is **~32% smaller**, delivers **bit-identical outputs**, and achieves performance **comparable to the original** BFloat16 model.
+
+Learn more in our [research paper](https://arxiv.org/abs/2504.11651).
+
+### 📄 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 +1,47 @@
+{
+  "dfloat11_config": {
+    "bytes_per_thread": 8,
+    "pattern_dict": {
+      "distilled_guidance_layer": [
+        "in_proj",
+        "layers.0.linear_1",
+        "layers.0.linear_2",
+        "layers.1.linear_1",
+        "layers.1.linear_2",
+        "layers.2.linear_1",
+        "layers.2.linear_2",
+        "layers.3.linear_1",
+        "layers.3.linear_2",
+        "layers.4.linear_1",
+        "layers.4.linear_2",
+        "out_proj"
+      ],
+      "transformer_blocks\\.\\d+": [
+        "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"
+      ],
+      "single_transformer_blocks\\.\\d+": [
+        "proj_mlp",
+        "proj_out",
+        "attn.to_q",
+        "attn.to_k",
+        "attn.to_v"
+      ]
+    },
+    "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 sha256:1946cfee6b41a528f251ac4582090934b8c4bc1d547e45ccbaede1fee351ec42
+size 25965232

distilled_guidance_layer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc37fff09ef35f550d9f310cf6a28ee9fac063b73bc75a819ed7f67a6e746751
+size 401204615

single_transformer_blocks_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0829592be0782ffb66f59e113f83fe9308b6feab407244809655df71f9bd54aa
+size 153532475

single_transformer_blocks_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b14c33ac7b922fdbd1ff9aa1e7895cf078358409e437b3e602d6835d0af131
+size 153580561

single_transformer_blocks_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e511e5b5d9b9426ce4bcddc5262192c672e1dbb8e3ddde55c47a688884ef73
+size 153574349

single_transformer_blocks_11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e6bd200972b19d66c50eab42dd0027706a966df3119681ed5e6ab311a6cef0
+size 153639119

single_transformer_blocks_12.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca14768358c316bb9903706da8498f4f68099116b058abbc51dff2d826c4b18e
+size 153605104

single_transformer_blocks_13.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44721502fff0f6ba54b9c737aa43bde143b01ba01f9968a0ebd99235dd7475f
+size 153654212

single_transformer_blocks_14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25822a1ef6d542638cda48f7daeee92e52cd0f6cb8f9c478c16a35ae987920de
+size 153711224

single_transformer_blocks_15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ab9eb274fb3c2b7ae3da59345f8d2234ae3d672f2e89a1b3d17d3752b7afd0
+size 153736678

single_transformer_blocks_16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4e023c35d13846aebfb1133e10f6fb1244ae5acb19f9aec473063cc28230b5
+size 153727163

single_transformer_blocks_17.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79caabbca55017c3ff828fc055c71562fe1eab071250648203318acd2962ba5d
+size 153801637

single_transformer_blocks_18.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c7a726ab91e8fabe9bc3d117dc8c132bb50d90f232472f433be5a9ff10674a
+size 153753097

single_transformer_blocks_19.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4ff424acbcec459571e1fd3c74394a38fbd2b3a355038e85160457d5f98341
+size 153702285

single_transformer_blocks_2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaabe701b4b4d7f06f5efbf9d63a42303c42711c12ed0147bec8325c3edf539
+size 153577280

single_transformer_blocks_20.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb0caf30338e5fa0140ce6408474122a6c68b2d1351674b9923958d6482893f
+size 153743696

single_transformer_blocks_21.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23dd0c2c914b0d936f9c109a937a6d026fb258588d6ac1fea657aac598f3b98
+size 153718684

single_transformer_blocks_22.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6961ab68343d9a11e2293614eb4003bcc397e78816ecb0e5c094cee736fe9d7
+size 153732357

single_transformer_blocks_23.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80d89c28c3a0fd2e52d6e516659046351310b6fd0166bcc9e39ae77db1ab9de
+size 153726532

single_transformer_blocks_24.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d8baa7d3de2ae3956207bdb65b459dfa93cb7e32fbb80b5a53cbeca2a6f13e
+size 153697483

single_transformer_blocks_25.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4a14e1e8bb2422d0ecc8877a4fe6ee52919ea5c64f07a1d011cd65002dde52
+size 153769908

single_transformer_blocks_26.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cce65a82a6375079eeee756e0b9df1f2047320045e9d94d01bb36df00d7f29
+size 153730023

single_transformer_blocks_27.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7ff4b9f00adaf43e63766cce1f9f5a8cff4de78697aad96a704a418ff92f6d
+size 153840436

single_transformer_blocks_28.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118cef7112842205b1961b6a6fc7e77901868f672f6a80d91b0e48f51b76d49b
+size 153855498

single_transformer_blocks_29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca1587072c59a67cdb27d1c2af373af10219f5b6c5b20e74c4ba623062364cb
+size 153878188

single_transformer_blocks_3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee77cd637cf9c37a77d39347e3852395be2a19b1c934a8df4cb197e6fb257213
+size 153574626

single_transformer_blocks_30.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f0ff84c736bb35872cec1c3f15d0a334e7151ee6e566360ab988a12334c5d5
+size 153942713

single_transformer_blocks_31.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d2c943125b76227e92bfbbc2e369251cb558f159d8c5d992992379927b0d20
+size 153936905

single_transformer_blocks_32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939fa460509507a702e9bca53045a4a7c2ed419becd8b175220d68c58cec4ea8
+size 153994729

single_transformer_blocks_33.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7eb59a005e87d78b2dfe4641c63a8a59ff91772a66e4311866da0363aaba511
+size 154001403

single_transformer_blocks_34.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ab1b7f99d68c97d2a8b727ec8a762ffc37734eb6b0d6afd9eef6fb78e8454e
+size 154455241

single_transformer_blocks_35.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef31957138390ea0b69067266440c2ba5a161cc6ba8d7e3466d353e7130a1452
+size 154444165

single_transformer_blocks_36.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786a2393c6557c8ff264c346da2847c59cd655fd4f5096a3933d79d20911f0d3
+size 154497870

single_transformer_blocks_37.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0accf9c11f10fd7eb540ff4eddafcfc0577e15220b99272fbbf244189984ef
+size 157063591

single_transformer_blocks_4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c6f7bc97e278446e8702ee2295aef709f455490572d5068cbbca9470df6530
+size 153548760

single_transformer_blocks_5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d23a39b5017a35b1413ce7a33a02b5244da0403ccfcb5c7f7936bb08b00314e
+size 153558605

single_transformer_blocks_6.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4960ac1498564734c74308e5c1a71346df7f934138dd4ab4db1ea29531ba405
+size 153563223

single_transformer_blocks_7.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b888ec5a15b5eef16c4fdf9f32301b15ac78288544e71effc835896cd6a89d
+size 153577408

single_transformer_blocks_8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31d6f80271e51986d0f49feb9a9d71a20911d5c43dac699657623a38dcd9e75
+size 153570142

single_transformer_blocks_9.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d12cd5750dc9e27c9b2d5c2a1dd92786c8e943defe4c6a119c0d235f82b701a
+size 153585371

transformer_blocks_0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ced1b93e41425e9f0f377d6d098efa82790512f6ab3695e440f8b6a39f8b206
+size 315157302

transformer_blocks_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44cd22bdbe2b648f7c0e1a5280b11cd1217a368c73985d047968dc876287186f
+size 313792761

transformer_blocks_10.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f366c2ada98c070b13d5760e38788bcb93cd9fb1f14d8dc34e623aca7a5072
+size 309281754

transformer_blocks_11.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b308bd897ee6f8e573aa8f76058fa35768fa82e6e55c3174ebd1f3659a080a
+size 309021532

transformer_blocks_12.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ab4eab0195ecfce93719f14ed63959dd940266569622ca72a0cc8c174289a8
+size 308827255

transformer_blocks_13.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef0c70cff677f13ba03b8adcbb32a6f7f6d9d1051992e848cbd213f62784b7b
+size 309862753

transformer_blocks_14.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b1c97d1249f4ced0ae0d710ae9658e5898fb6aca6cb71b349b62b3bb7605e5
+size 308447092

transformer_blocks_15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e098eb849a24c6b0bab596a53cb446e07322be34e7d5f28e96f5e34bc06666a
+size 307708330