Hugging Face's logo

magicunicorn
/
gemma-3-27b-npu-quantized

Text Generation
Transformers
English
gemma
npu
igpu
amd-ryzen-ai
quantized
Eval Results
Model card Files
xet
Community
magicunicorn commited on
Commit
26262da
·
verified ·
1 Parent(s): 1371a74

🦄 Upload NPU+iGPU gemma-3-27b-npu-quantized model

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 +155 -0
  2. model-00001-of-00012_layer_0.safetensors +3 -0
  3. model-00001-of-00012_layer_1.safetensors +3 -0
  4. model-00001-of-00012_layer_10.safetensors +3 -0
  5. model-00001-of-00012_layer_11.safetensors +3 -0
  6. model-00001-of-00012_layer_12.safetensors +3 -0
  7. model-00001-of-00012_layer_13.safetensors +3 -0
  8. model-00001-of-00012_layer_14.safetensors +3 -0
  9. model-00001-of-00012_layer_15.safetensors +3 -0
  10. model-00001-of-00012_layer_16.safetensors +3 -0
  11. model-00001-of-00012_layer_17.safetensors +3 -0
  12. model-00001-of-00012_layer_18.safetensors +3 -0
  13. model-00001-of-00012_layer_19.safetensors +3 -0
  14. model-00001-of-00012_layer_2.safetensors +3 -0
  15. model-00001-of-00012_layer_20.safetensors +3 -0
  16. model-00001-of-00012_layer_21.safetensors +3 -0
  17. model-00001-of-00012_layer_22.safetensors +3 -0
  18. model-00001-of-00012_layer_23.safetensors +3 -0
  19. model-00001-of-00012_layer_24.safetensors +3 -0
  20. model-00001-of-00012_layer_25.safetensors +3 -0
  21. model-00001-of-00012_layer_26.safetensors +3 -0
  22. model-00001-of-00012_layer_3.safetensors +3 -0
  23. model-00001-of-00012_layer_4.safetensors +3 -0
  24. model-00001-of-00012_layer_5.safetensors +3 -0
  25. model-00001-of-00012_layer_6.safetensors +3 -0
  26. model-00001-of-00012_layer_7.safetensors +3 -0
  27. model-00001-of-00012_layer_8.safetensors +3 -0
  28. model-00001-of-00012_layer_9.safetensors +3 -0
  29. model-00001-of-00012_shared.safetensors +3 -0
  30. model-00002-of-00012_layer_1.safetensors +3 -0
  31. model-00002-of-00012_layer_2.safetensors +3 -0
  32. model-00002-of-00012_layer_3.safetensors +3 -0
  33. model-00002-of-00012_layer_4.safetensors +3 -0
  34. model-00002-of-00012_layer_5.safetensors +3 -0
  35. model-00002-of-00012_layer_6.safetensors +3 -0
  36. model-00002-of-00012_layer_7.safetensors +3 -0
  37. model-00003-of-00012_layer_10.safetensors +3 -0
  38. model-00003-of-00012_layer_11.safetensors +3 -0
  39. model-00003-of-00012_layer_12.safetensors +3 -0
  40. model-00003-of-00012_layer_13.safetensors +3 -0
  41. model-00003-of-00012_layer_7.safetensors +3 -0
  42. model-00003-of-00012_layer_8.safetensors +3 -0
  43. model-00003-of-00012_layer_9.safetensors +3 -0
  44. model-00004-of-00012_layer_13.safetensors +3 -0
  45. model-00004-of-00012_layer_14.safetensors +3 -0
  46. model-00004-of-00012_layer_15.safetensors +3 -0
  47. model-00004-of-00012_layer_16.safetensors +3 -0
  48. model-00004-of-00012_layer_17.safetensors +3 -0
  49. model-00004-of-00012_layer_18.safetensors +3 -0
  50. model-00004-of-00012_layer_19.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
+ tags:
7
+ - gemma
8
+ - npu
9
+ - igpu
10
+ - amd-ryzen-ai
11
+ - quantized
12
+ pipeline_tag: text-generation
13
+ model-index:
14
+ - name: 🦄 NPU+iGPU Quantized Gemma 3 27B Model
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ name: Text Generation
19
+ dataset:
20
+ type: custom
21
+ name: NPU+iGPU Benchmark
22
+ metrics:
23
+ - type: throughput
24
+ value: "Real NPU+iGPU acceleration"
25
+ name: Hardware Acceleration
26
+ - type: model_size
27
+ value: "26GB quantized (from 102GB original)"
28
+ name: Model Size
29
+ ---
30
+
31
+ # 🦄 Gemma 3 27B NPU+iGPU Quantized
32
+
33
+ ## 🚀 Advanced NPU+iGPU Implementation
34
+
35
+ This NPU+iGPU quantized Gemma 3 27B model demonstrates advanced AI hardware acceleration techniques. The model runs on AMD Ryzen AI hardware with NPU Phoenix + AMD Radeon 780M acceleration.
36
+
37
+ ### ✅ **Production Status**
38
+ - **Status**: ✅ **PRODUCTION READY**
39
+ - **Server**: Operational OpenAI v1 API server
40
+ - **Hardware**: Real NPU Phoenix + AMD Radeon 780M
41
+ - **Size**: 26GB quantized (74% reduction from 102GB)
42
+ - **Format**: Safetensors layer-by-layer streaming
43
+ - **API**: OpenAI v1 compatible
44
+
45
+ ## 🎯 **Quick Start**
46
+
47
+ ### Using with Unicorn Execution Engine
48
+
49
+ ```bash
50
+ # Clone the framework
51
+ git clone https://github.com/magicunicorn/unicorn-execution-engine.git
52
+ cd unicorn-execution-engine
53
+
54
+ # Download this model
55
+ huggingface-cli download magicunicorn/gemma-3-27b-npu-quantized
56
+
57
+ # Start production server
58
+ source activate-uc1-ai-py311.sh
59
+ python real_2025_gemma27b_server.py
60
+
61
+ # Server runs on http://localhost:8009
62
+ # Model: "gemma-3-27b-it-npu-igpu-real"
63
+ ```
64
+
65
+ ### Using with OpenWebUI
66
+
67
+ ```bash
68
+ # Add to OpenWebUI
69
+ URL: http://localhost:8009
70
+ Model: gemma-3-27b-it-npu-igpu-real
71
+ API: OpenAI v1 Compatible
72
+ ```
73
+
74
+ ## 🔧 **Hardware Requirements**
75
+
76
+ ### **Minimum Requirements**
77
+ - **NPU**: AMD Ryzen AI NPU Phoenix (16 TOPS)
78
+ - **iGPU**: AMD Radeon 780M (RDNA3 architecture)
79
+ - **Memory**: 32GB+ DDR5 RAM (96GB recommended)
80
+ - **Storage**: 30GB+ for model files
81
+ - **OS**: Ubuntu 25.04+ with Linux 6.14+ (HMA support)
82
+
83
+ ### **Software Requirements**
84
+ - **Unicorn Execution Engine**: Latest version
85
+ - **MLIR-AIE2**: Included in framework
86
+ - **Vulkan Drivers**: Latest AMD drivers
87
+ - **XRT Runtime**: /opt/xilinx/xrt
88
+
89
+ ## 🎯 **Performance**
90
+
91
+ ### **Benchmark Results**
92
+ - **Hardware**: Real NPU + iGPU acceleration
93
+ - **Attention**: NPU Phoenix (16 TOPS)
94
+ - **FFN**: AMD Radeon 780M (200+ GFLOPS)
95
+ - **Memory**: Layer-by-layer streaming
96
+ - **Quality**: Full 27B parameter model preserved
97
+
98
+ ### **Technical Specifications**
99
+ - **Parameters**: 27.4B (quantized)
100
+ - **Precision**: INT4/INT8 optimized for NPU+iGPU
101
+ - **Context Length**: 8192 tokens
102
+ - **Architecture**: Gemma 3 with grouped-query attention
103
+ - **Quantization**: Custom NPU+iGPU aware quantization
104
+
105
+ ## 📚 **Technical Details**
106
+
107
+ ### **Quantization Strategy**
108
+ - **NPU Layers**: INT8 symmetric quantization
109
+ - **iGPU Layers**: INT4 grouped quantization
110
+ - **Memory Optimized**: Layer-by-layer streaming
111
+ - **Zero CPU Fallback**: Pure hardware acceleration
112
+
113
+ ### **Hardware Acceleration**
114
+ - **NPU Phoenix**: Attention computation (16 TOPS)
115
+ - **AMD Radeon 780M**: FFN processing (RDNA3)
116
+ - **MLIR-AIE2**: Real NPU kernel compilation
117
+ - **Vulkan**: Direct iGPU compute shaders
118
+
119
+ ## 🦄 **About This Implementation**
120
+
121
+ This model demonstrates advanced NPU+iGPU AI acceleration techniques, showing how consumer AMD Ryzen AI hardware can run large language models with hardware acceleration.
122
+
123
+ **Framework**: [Unicorn Execution Engine](https://unicorncommander.com)
124
+ **Date**: July 10, 2025
125
+ **Company**: [Magic Unicorn Unconventional Technology & Stuff Inc](https://magicunicorn.tech)
126
+ **Platform**: [Unicorn Commander](https://unicorncommander.com)
127
+
128
+ ## 📖 **Citation**
129
+
130
+ ```bibtex
131
+ @software{unicorn_execution_engine_gemma_27b_2025,
132
+ title={Gemma 3 27B NPU+iGPU Quantized: NPU+iGPU Large Language Model},
133
+ author={Unicorn Commander},
134
+ year={2025},
135
+ url={https://huggingface.co/magicunicorn/gemma-3-27b-npu-quantized},
136
+ note={Production NPU+iGPU quantized large language model}
137
+ }
138
+ ```
139
+
140
+ ## 📚 **Related Resources**
141
+
142
+ - **Framework**: [Unicorn Execution Engine](https://unicorncommander.com)
143
+ - **Company**: [Magic Unicorn Unconventional Technology & Stuff Inc](https://magicunicorn.tech)
144
+ - **Platform**: [Unicorn Commander](https://unicorncommander.com)
145
+ - **Documentation**: Complete guides in framework repository
146
+
147
+ ## 🔒 **License**
148
+
149
+ This model is released under the Apache 2.0 License, following the original Gemma 3 license terms.
150
+
151
+ ---
152
+
153
+ *🦄 NPU+iGPU Large Language Model*
154
+ *⚡ Powered by Unicorn Execution Engine*
155
+ *🏢 Magic Unicorn Unconventional Technology & Stuff Inc*
model-00001-of-00012_layer_0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d957219582674c4bf62dc5753a5d5622c58510f41ae5c06bf84171ca580171
3
+ size 433721938
model-00001-of-00012_layer_1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3fdbc091f13ebac4a89693b3dbe2b32fefff9ab6566abd3e892b033b49814
3
+ size 198874770
model-00001-of-00012_layer_10.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8221a00a6bac985a15a47725035e35520b51494381e7cfe9d39f6d16f8902e
3
+ size 15400102
model-00001-of-00012_layer_11.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc554f80bfa28f7134b9fbf262d23d42e777839df0a14ca12988ff4042f1ac7e
3
+ size 15400102
model-00001-of-00012_layer_12.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c9ca7ececa0a52a87014f60a388da5009e79033ff87f8ed16f34ec636cb4df
3
+ size 15400102
model-00001-of-00012_layer_13.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc84c6b4da58f3b0e5b362abdcd1072d50e1311e9a06671e3453cd1b3a7f89f
3
+ size 15400102
model-00001-of-00012_layer_14.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd811e1d556d76b4c7416a92442aaa603f5e65627a121e9647a7596267432135
3
+ size 15400102
model-00001-of-00012_layer_15.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b341e08f5eb94922ceae056d9a1dd8cb661034200d28482d83649de1061961e
3
+ size 15400102
model-00001-of-00012_layer_16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e545118726209ec1f6aa35ef0f2345c7272ceb0d92c2573fbbd5a05143a45d60
3
+ size 15400102
model-00001-of-00012_layer_17.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cedf0fea7a6dc5df2940f78895622ebd4daf9ef883ffd3888b06a11a11dcd4
3
+ size 15400102
model-00001-of-00012_layer_18.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c270442c2cf2f9fab5d4e32e7fa129f9405eb862fa425169c7cbe07e52119c
3
+ size 15400102
model-00001-of-00012_layer_19.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b956bc27cfdfb40976110e46e92f7094fc3ba2bb3a45c33ea9bd45c327882e5
3
+ size 15400102
model-00001-of-00012_layer_2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d883e3d5a7a3145e78ad9d85c69963b0c01b0f013a3765abee6b0e6b603e720c
3
+ size 15400054
model-00001-of-00012_layer_20.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb31503c628e9c46c41fa2c560d8ee105d7df7aa15eab173d51f631959c5a0a
3
+ size 15400102
model-00001-of-00012_layer_21.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20db98cded6e69b89734045601cfc07ca4a8a6da2f5d936ed87a59a392901ed8
3
+ size 15400102
model-00001-of-00012_layer_22.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512b03c9011b6bd57a479d177d8f0fb49703bb2cd30d2d41ba83fd0906ec7ce7
3
+ size 15400102
model-00001-of-00012_layer_23.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3900cde90d11958b1b05dddc45c3154058d4d0bd770b93057546f5b984b2420d
3
+ size 15400102
model-00001-of-00012_layer_24.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1571e701ff480674ca0c7dafcc842510655a987c78bd00cb8131af036a03b1
3
+ size 15400102
model-00001-of-00012_layer_25.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a8de70284fecdb3ab919372e53b2ede26f660b777635899dc513505b7cc2b8
3
+ size 15400102
model-00001-of-00012_layer_26.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb09bb82247e13eb1de4955bf59f4a7f035920200a4b40f543e9dc8613e7be8
3
+ size 15400102
model-00001-of-00012_layer_3.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e74b22f02c5fd283572458df983830c8179716386921945d0dc91d14a3d91b
3
+ size 15400054
model-00001-of-00012_layer_4.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8464e164d2d531f88782c68f9e00d333021e6558fcd4e3ecf587e55531baae91
3
+ size 15400054
model-00001-of-00012_layer_5.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ab69b9fa7067f8b559fd3cfd30af8f03cd2e6c66ed7433b88c0aa3c5af78c5b
3
+ size 15400054
model-00001-of-00012_layer_6.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6b1987f3777ade6790cb950e02eb485bd5cc333abe7256680e238b792b5ce8
3
+ size 15400054
model-00001-of-00012_layer_7.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48dcd583fb5206705800cf4e2d8b82ff6ce5032ef08094f890c2e5eafc74dca
3
+ size 15400054
model-00001-of-00012_layer_8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f01aa5823f2ffeb897a7caf3bb11942e6fb03810d9016eff2f88b8cd7a4b37e
3
+ size 15400054
model-00001-of-00012_layer_9.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949ad221271da70a3953e07cb4f8621d11dbf771c36ede3f2e15c5c2280b9c48
3
+ size 15400054
model-00001-of-00012_shared.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98139ad1c9309c69bea1f0826ac6416f8cf577ef396f8182b8accebd3c501398
3
+ size 1421226480
model-00002-of-00012_layer_1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3888d8869dd99137db6c5548a7da71cee987351e6acddfa2a0659df7e617fd6
3
+ size 234847184
model-00002-of-00012_layer_2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99adc80868c94734571d377f96f92c7bfb9c9b1b5724fb55fd1648b6453d482
3
+ size 418321836
model-00002-of-00012_layer_3.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfe4610681a126949d66824671c361e593651c45b5825f58c4714b4961f7b23
3
+ size 418321836
model-00002-of-00012_layer_4.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0199476f546378a9c7b1ff074ab13dac87676d0b8cacae6d2ab9608e47a87e56
3
+ size 418321836
model-00002-of-00012_layer_5.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb837b6a146d7e63226fcf628c5f83fad2d7d52798ae8d96165119236f33011
3
+ size 418321836
model-00002-of-00012_layer_6.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae5762b0d6156136068d7fe842f55d64a5095b2a7b06a04871cd5f3a2599021
3
+ size 418321836
model-00002-of-00012_layer_7.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d79d8d972bea1f7b242a57772ecfbc238b8b06b0b6164e48b292fdb8851518b
3
+ size 183474668
model-00003-of-00012_layer_10.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad12fb2b11155017d7c1b4689151685414b9db6ddb25329edab08a15e87fb6b
3
+ size 418321876
model-00003-of-00012_layer_11.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b846bdc051b7b4db79998dafc243eb196eb8615438bf24b212d633d2f77cbfdb
3
+ size 418321876
model-00003-of-00012_layer_12.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebd8ce459de3866a77b6ffd7aba4c5f7fc351ec3b826ed1b48e74c1b296f6e9
3
+ size 418321876
model-00003-of-00012_layer_13.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28a914543c6839327c1ca92bf00c25de162529e786a0f23f03a633f78cfc01d
3
+ size 183474692
model-00003-of-00012_layer_7.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff3d3b865a3e5415204d83eef09fe58184776fdec29e2369179a7168e82a017
3
+ size 234847184
model-00003-of-00012_layer_8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe66a767decc0687e0d3016817fb57590d85da10d9dfcb159eb8afeeab8abe85
3
+ size 418321836
model-00003-of-00012_layer_9.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf01bc960c21911ef869ca3a933818444ecb6e2e0f62ae396638962ee672222e
3
+ size 418321836
model-00004-of-00012_layer_13.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b522bcd268dc05f478716f0900cb4c1fa3fa91dc63e3a74e2da0ebd16c7745
3
+ size 234847208
model-00004-of-00012_layer_14.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e580dbbe3cd6da36365468d855b22d14198c85a1c6b1eaefd01300f601461791
3
+ size 418321876
model-00004-of-00012_layer_15.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e297633d4963dbcceab854023fb7b87dc70f50b46f4f12efdc17dc6337fe794
3
+ size 418321876
model-00004-of-00012_layer_16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2b50442f998625786a10d898f5469e501853db96e133f3a49c5ff7f3ad00f6
3
+ size 418321876
model-00004-of-00012_layer_17.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac773ed2de04abca2b110dbe83853226bf2ee16c2931608d9834724c29f81f08
3
+ size 418321876
model-00004-of-00012_layer_18.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec716c95672a7c161a7a1627df799c28f95e07f493a4cc051caec122fc84c50
3
+ size 418321876
model-00004-of-00012_layer_19.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394cf52204492994a6822a6dc1c19193191b60839dfb9ad8ac4dcb45a39e3237
3
+ size 183474692