LeanQuant commited on
Commit
0825617
·
verified ·
1 Parent(s): 91fca7a

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +92 -0
  2. config.json +47 -0
  3. diffusion_pytorch_model.safetensors +3 -0
  4. distilled_guidance_layer.safetensors +3 -0
  5. single_transformer_blocks_0.safetensors +3 -0
  6. single_transformer_blocks_1.safetensors +3 -0
  7. single_transformer_blocks_10.safetensors +3 -0
  8. single_transformer_blocks_11.safetensors +3 -0
  9. single_transformer_blocks_12.safetensors +3 -0
  10. single_transformer_blocks_13.safetensors +3 -0
  11. single_transformer_blocks_14.safetensors +3 -0
  12. single_transformer_blocks_15.safetensors +3 -0
  13. single_transformer_blocks_16.safetensors +3 -0
  14. single_transformer_blocks_17.safetensors +3 -0
  15. single_transformer_blocks_18.safetensors +3 -0
  16. single_transformer_blocks_19.safetensors +3 -0
  17. single_transformer_blocks_2.safetensors +3 -0
  18. single_transformer_blocks_20.safetensors +3 -0
  19. single_transformer_blocks_21.safetensors +3 -0
  20. single_transformer_blocks_22.safetensors +3 -0
  21. single_transformer_blocks_23.safetensors +3 -0
  22. single_transformer_blocks_24.safetensors +3 -0
  23. single_transformer_blocks_25.safetensors +3 -0
  24. single_transformer_blocks_26.safetensors +3 -0
  25. single_transformer_blocks_27.safetensors +3 -0
  26. single_transformer_blocks_28.safetensors +3 -0
  27. single_transformer_blocks_29.safetensors +3 -0
  28. single_transformer_blocks_3.safetensors +3 -0
  29. single_transformer_blocks_30.safetensors +3 -0
  30. single_transformer_blocks_31.safetensors +3 -0
  31. single_transformer_blocks_32.safetensors +3 -0
  32. single_transformer_blocks_33.safetensors +3 -0
  33. single_transformer_blocks_34.safetensors +3 -0
  34. single_transformer_blocks_35.safetensors +3 -0
  35. single_transformer_blocks_36.safetensors +3 -0
  36. single_transformer_blocks_37.safetensors +3 -0
  37. single_transformer_blocks_4.safetensors +3 -0
  38. single_transformer_blocks_5.safetensors +3 -0
  39. single_transformer_blocks_6.safetensors +3 -0
  40. single_transformer_blocks_7.safetensors +3 -0
  41. single_transformer_blocks_8.safetensors +3 -0
  42. single_transformer_blocks_9.safetensors +3 -0
  43. transformer_blocks_0.safetensors +3 -0
  44. transformer_blocks_1.safetensors +3 -0
  45. transformer_blocks_10.safetensors +3 -0
  46. transformer_blocks_11.safetensors +3 -0
  47. transformer_blocks_12.safetensors +3 -0
  48. transformer_blocks_13.safetensors +3 -0
  49. transformer_blocks_14.safetensors +3 -0
  50. transformer_blocks_15.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - lodestones/Chroma
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: `lodestones/Chroma`
14
+
15
+ 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**.
16
+
17
+ 🔥🔥🔥 Thanks to DFloat11 compression, Chroma can now run smoothly on a single 16GB GPU without any quality loss. 🔥🔥🔥
18
+
19
+ ### 📊 Performance Comparison
20
+
21
+ | Metric | Chroma (BFloat16) | Chroma (DFloat11) |
22
+ | ----------------------------------------------- | ------------------- | ------------------- |
23
+ | Model Size | 17.80 GB | 12.16 GB |
24
+ | Peak GPU Memory<br>(1024×1024 image generation) | 18.33 GB | 13.26 GB |
25
+ | Generation Time<br>(A100 GPU) | 56 seconds | 59 seconds |
26
+
27
+ ### 🔧 How to Use
28
+
29
+ 1. Install or upgrade the DFloat11 pip package *(installs the CUDA kernel automatically; requires a CUDA-compatible GPU and PyTorch installed)*:
30
+
31
+ ```bash
32
+ pip install -U dfloat11[cuda12]
33
+ # or if you have CUDA version 11:
34
+ # pip install -U dfloat11[cuda11]
35
+ ```
36
+
37
+ 2. Install or upgrade the diffusers library.
38
+
39
+ ```bash
40
+ pip install -U diffusers
41
+ ```
42
+
43
+ 3. To use the DFloat11 model, run the following example code in Python:
44
+
45
+ ```python
46
+ import torch
47
+ from diffusers import ChromaTransformer2DModel, ChromaPipeline
48
+ from transformers.modeling_utils import no_init_weights
49
+ from dfloat11 import DFloat11Model
50
+
51
+ with no_init_weights():
52
+ transformer = ChromaTransformer2DModel().to(torch.bfloat16)
53
+
54
+ DFloat11Model.from_pretrained(
55
+ "DFloat11/Chroma-DF11",
56
+ bfloat16_model=transformer,
57
+ device="cpu",
58
+ )
59
+
60
+ pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", transformer=transformer, torch_dtype=torch.bfloat16)
61
+ pipe.enable_model_cpu_offload()
62
+
63
+ prompt = [
64
+ "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."
65
+ ]
66
+ negative_prompt = ["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"]
67
+
68
+ image = pipe(
69
+ prompt=prompt,
70
+ negative_prompt=negative_prompt,
71
+ generator=torch.Generator("cpu").manual_seed(433),
72
+ num_inference_steps=40,
73
+ guidance_scale=3.0,
74
+ ).images[0]
75
+
76
+ image.save("chroma-output.png")
77
+ ```
78
+
79
+
80
+ ### 🔍 How It Works
81
+
82
+ 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.
83
+
84
+ The result is a model that is **~32% smaller**, delivers **bit-identical outputs**, and achieves performance **comparable to the original** BFloat16 model.
85
+
86
+ Learn more in our [research paper](https://arxiv.org/abs/2504.11651).
87
+
88
+ ### 📄 Learn More
89
+
90
+ * **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
91
+ * **GitHub**: [https://github.com/LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
92
+ * **HuggingFace**: [https://huggingface.co/DFloat11](https://huggingface.co/DFloat11)
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dfloat11_config": {
3
+ "bytes_per_thread": 8,
4
+ "pattern_dict": {
5
+ "distilled_guidance_layer": [
6
+ "in_proj",
7
+ "layers.0.linear_1",
8
+ "layers.0.linear_2",
9
+ "layers.1.linear_1",
10
+ "layers.1.linear_2",
11
+ "layers.2.linear_1",
12
+ "layers.2.linear_2",
13
+ "layers.3.linear_1",
14
+ "layers.3.linear_2",
15
+ "layers.4.linear_1",
16
+ "layers.4.linear_2",
17
+ "out_proj"
18
+ ],
19
+ "transformer_blocks\\.\\d+": [
20
+ "attn.to_q",
21
+ "attn.to_k",
22
+ "attn.to_v",
23
+ "attn.add_k_proj",
24
+ "attn.add_v_proj",
25
+ "attn.add_q_proj",
26
+ "attn.to_out.0",
27
+ "attn.to_add_out",
28
+ "ff.net.0.proj",
29
+ "ff.net.2",
30
+ "ff_context.net.0.proj",
31
+ "ff_context.net.2"
32
+ ],
33
+ "single_transformer_blocks\\.\\d+": [
34
+ "proj_mlp",
35
+ "proj_out",
36
+ "attn.to_q",
37
+ "attn.to_k",
38
+ "attn.to_v"
39
+ ]
40
+ },
41
+ "threads_per_block": [
42
+ 512
43
+ ],
44
+ "version": "0.2.0"
45
+ },
46
+ "model_type": "llama"
47
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1946cfee6b41a528f251ac4582090934b8c4bc1d547e45ccbaede1fee351ec42
3
+ size 25965232
distilled_guidance_layer.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc37fff09ef35f550d9f310cf6a28ee9fac063b73bc75a819ed7f67a6e746751
3
+ size 401204615
single_transformer_blocks_0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0829592be0782ffb66f59e113f83fe9308b6feab407244809655df71f9bd54aa
3
+ size 153532475
single_transformer_blocks_1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b14c33ac7b922fdbd1ff9aa1e7895cf078358409e437b3e602d6835d0af131
3
+ size 153580561
single_transformer_blocks_10.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e511e5b5d9b9426ce4bcddc5262192c672e1dbb8e3ddde55c47a688884ef73
3
+ size 153574349
single_transformer_blocks_11.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e6bd200972b19d66c50eab42dd0027706a966df3119681ed5e6ab311a6cef0
3
+ size 153639119
single_transformer_blocks_12.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca14768358c316bb9903706da8498f4f68099116b058abbc51dff2d826c4b18e
3
+ size 153605104
single_transformer_blocks_13.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44721502fff0f6ba54b9c737aa43bde143b01ba01f9968a0ebd99235dd7475f
3
+ size 153654212
single_transformer_blocks_14.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25822a1ef6d542638cda48f7daeee92e52cd0f6cb8f9c478c16a35ae987920de
3
+ size 153711224
single_transformer_blocks_15.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ab9eb274fb3c2b7ae3da59345f8d2234ae3d672f2e89a1b3d17d3752b7afd0
3
+ size 153736678
single_transformer_blocks_16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4e023c35d13846aebfb1133e10f6fb1244ae5acb19f9aec473063cc28230b5
3
+ size 153727163
single_transformer_blocks_17.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79caabbca55017c3ff828fc055c71562fe1eab071250648203318acd2962ba5d
3
+ size 153801637
single_transformer_blocks_18.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c7a726ab91e8fabe9bc3d117dc8c132bb50d90f232472f433be5a9ff10674a
3
+ size 153753097
single_transformer_blocks_19.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4ff424acbcec459571e1fd3c74394a38fbd2b3a355038e85160457d5f98341
3
+ size 153702285
single_transformer_blocks_2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eaabe701b4b4d7f06f5efbf9d63a42303c42711c12ed0147bec8325c3edf539
3
+ size 153577280
single_transformer_blocks_20.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb0caf30338e5fa0140ce6408474122a6c68b2d1351674b9923958d6482893f
3
+ size 153743696
single_transformer_blocks_21.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23dd0c2c914b0d936f9c109a937a6d026fb258588d6ac1fea657aac598f3b98
3
+ size 153718684
single_transformer_blocks_22.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6961ab68343d9a11e2293614eb4003bcc397e78816ecb0e5c094cee736fe9d7
3
+ size 153732357
single_transformer_blocks_23.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80d89c28c3a0fd2e52d6e516659046351310b6fd0166bcc9e39ae77db1ab9de
3
+ size 153726532
single_transformer_blocks_24.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d8baa7d3de2ae3956207bdb65b459dfa93cb7e32fbb80b5a53cbeca2a6f13e
3
+ size 153697483
single_transformer_blocks_25.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4a14e1e8bb2422d0ecc8877a4fe6ee52919ea5c64f07a1d011cd65002dde52
3
+ size 153769908
single_transformer_blocks_26.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cce65a82a6375079eeee756e0b9df1f2047320045e9d94d01bb36df00d7f29
3
+ size 153730023
single_transformer_blocks_27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7ff4b9f00adaf43e63766cce1f9f5a8cff4de78697aad96a704a418ff92f6d
3
+ size 153840436
single_transformer_blocks_28.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118cef7112842205b1961b6a6fc7e77901868f672f6a80d91b0e48f51b76d49b
3
+ size 153855498
single_transformer_blocks_29.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca1587072c59a67cdb27d1c2af373af10219f5b6c5b20e74c4ba623062364cb
3
+ size 153878188
single_transformer_blocks_3.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee77cd637cf9c37a77d39347e3852395be2a19b1c934a8df4cb197e6fb257213
3
+ size 153574626
single_transformer_blocks_30.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f0ff84c736bb35872cec1c3f15d0a334e7151ee6e566360ab988a12334c5d5
3
+ size 153942713
single_transformer_blocks_31.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40d2c943125b76227e92bfbbc2e369251cb558f159d8c5d992992379927b0d20
3
+ size 153936905
single_transformer_blocks_32.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939fa460509507a702e9bca53045a4a7c2ed419becd8b175220d68c58cec4ea8
3
+ size 153994729
single_transformer_blocks_33.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7eb59a005e87d78b2dfe4641c63a8a59ff91772a66e4311866da0363aaba511
3
+ size 154001403
single_transformer_blocks_34.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ab1b7f99d68c97d2a8b727ec8a762ffc37734eb6b0d6afd9eef6fb78e8454e
3
+ size 154455241
single_transformer_blocks_35.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef31957138390ea0b69067266440c2ba5a161cc6ba8d7e3466d353e7130a1452
3
+ size 154444165
single_transformer_blocks_36.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786a2393c6557c8ff264c346da2847c59cd655fd4f5096a3933d79d20911f0d3
3
+ size 154497870
single_transformer_blocks_37.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0accf9c11f10fd7eb540ff4eddafcfc0577e15220b99272fbbf244189984ef
3
+ size 157063591
single_transformer_blocks_4.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c6f7bc97e278446e8702ee2295aef709f455490572d5068cbbca9470df6530
3
+ size 153548760
single_transformer_blocks_5.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d23a39b5017a35b1413ce7a33a02b5244da0403ccfcb5c7f7936bb08b00314e
3
+ size 153558605
single_transformer_blocks_6.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4960ac1498564734c74308e5c1a71346df7f934138dd4ab4db1ea29531ba405
3
+ size 153563223
single_transformer_blocks_7.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b888ec5a15b5eef16c4fdf9f32301b15ac78288544e71effc835896cd6a89d
3
+ size 153577408
single_transformer_blocks_8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31d6f80271e51986d0f49feb9a9d71a20911d5c43dac699657623a38dcd9e75
3
+ size 153570142
single_transformer_blocks_9.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d12cd5750dc9e27c9b2d5c2a1dd92786c8e943defe4c6a119c0d235f82b701a
3
+ size 153585371
transformer_blocks_0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ced1b93e41425e9f0f377d6d098efa82790512f6ab3695e440f8b6a39f8b206
3
+ size 315157302
transformer_blocks_1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44cd22bdbe2b648f7c0e1a5280b11cd1217a368c73985d047968dc876287186f
3
+ size 313792761
transformer_blocks_10.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f366c2ada98c070b13d5760e38788bcb93cd9fb1f14d8dc34e623aca7a5072
3
+ size 309281754
transformer_blocks_11.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b308bd897ee6f8e573aa8f76058fa35768fa82e6e55c3174ebd1f3659a080a
3
+ size 309021532
transformer_blocks_12.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ab4eab0195ecfce93719f14ed63959dd940266569622ca72a0cc8c174289a8
3
+ size 308827255
transformer_blocks_13.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef0c70cff677f13ba03b8adcbb32a6f7f6d9d1051992e848cbd213f62784b7b
3
+ size 309862753
transformer_blocks_14.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b1c97d1249f4ced0ae0d710ae9658e5898fb6aca6cb71b349b62b3bb7605e5
3
+ size 308447092
transformer_blocks_15.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e098eb849a24c6b0bab596a53cb446e07322be34e7d5f28e96f5e34bc06666a
3
+ size 307708330