qaihm-bot commited on
Commit
210523e
·
verified ·
1 Parent(s): 9acc5db

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +34 -34
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: apache-2.0
4
  tags:
5
  - android
6
  pipeline_tag: text-generation
@@ -25,40 +25,40 @@ More details on model performance across various devices, can be found
25
 
26
  ### Model Details
27
 
28
- - **Model Type:** Text generation
29
  - **Model Stats:**
30
  - Model checkpoint: v1.5
31
  - Input resolution: 1x128 (seqlen can vary)
32
  - Number of parameters: 137M
33
  - Model size: 547 MB
34
 
35
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | Nomic-Embed-Text | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 10.366 ms | 0 - 18 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
38
- | Nomic-Embed-Text | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 9.091 ms | 0 - 27 MB | FP16 | NPU | [Nomic-Embed-Text.so](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.so) |
39
- | Nomic-Embed-Text | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 7.577 ms | 0 - 406 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
40
- | Nomic-Embed-Text | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 6.474 ms | 0 - 367 MB | FP16 | NPU | [Nomic-Embed-Text.so](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.so) |
41
- | Nomic-Embed-Text | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 7.378 ms | 0 - 361 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
42
- | Nomic-Embed-Text | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 6.192 ms | 0 - 325 MB | FP16 | NPU | Use Export Script |
43
- | Nomic-Embed-Text | SA7255P ADP | SA7255P | TFLITE | 186.821 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
44
- | Nomic-Embed-Text | SA7255P ADP | SA7255P | QNN | 181.79 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
45
- | Nomic-Embed-Text | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 10.671 ms | 0 - 19 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
46
- | Nomic-Embed-Text | SA8255 (Proxy) | SA8255P Proxy | QNN | 8.067 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
47
- | Nomic-Embed-Text | SA8295P ADP | SA8295P | TFLITE | 14.362 ms | 0 - 348 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
48
- | Nomic-Embed-Text | SA8295P ADP | SA8295P | QNN | 11.133 ms | 0 - 17 MB | FP16 | NPU | Use Export Script |
49
- | Nomic-Embed-Text | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 10.585 ms | 0 - 18 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
50
- | Nomic-Embed-Text | SA8650 (Proxy) | SA8650P Proxy | QNN | 8.09 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
51
- | Nomic-Embed-Text | SA8775P ADP | SA8775P | TFLITE | 15.449 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
52
- | Nomic-Embed-Text | SA8775P ADP | SA8775P | QNN | 12.237 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
53
- | Nomic-Embed-Text | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 186.821 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
54
- | Nomic-Embed-Text | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 181.79 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
55
- | Nomic-Embed-Text | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 10.581 ms | 0 - 20 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
56
- | Nomic-Embed-Text | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 8.065 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
57
- | Nomic-Embed-Text | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 15.449 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
58
- | Nomic-Embed-Text | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 12.237 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
59
- | Nomic-Embed-Text | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 13.287 ms | 0 - 401 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
60
- | Nomic-Embed-Text | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 11.382 ms | 0 - 366 MB | FP16 | NPU | Use Export Script |
61
- | Nomic-Embed-Text | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.34 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
62
 
63
 
64
 
@@ -120,12 +120,12 @@ python -m qai_hub_models.models.nomic_embed_text.export
120
  Profiling Results
121
  ------------------------------------------------------------
122
  Nomic-Embed-Text
123
- Device : Samsung Galaxy S23 (13)
124
- Runtime : TFLITE
125
- Estimated inference time (ms) : 10.4
126
- Estimated peak memory usage (MB): [0, 18]
127
- Total # Ops : 906
128
- Compute Unit(s) : NPU (906 ops)
129
  ```
130
 
131
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - android
6
  pipeline_tag: text-generation
 
25
 
26
  ### Model Details
27
 
28
+ - **Model Type:** Model_use_case.text_generation
29
  - **Model Stats:**
30
  - Model checkpoint: v1.5
31
  - Input resolution: 1x128 (seqlen can vary)
32
  - Number of parameters: 137M
33
  - Model size: 547 MB
34
 
35
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 34.455 ms | 105 - 465 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
38
+ | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 29.131 ms | 0 - 9 MB | NPU | Use Export Script |
39
+ | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 12.916 ms | 0 - 398 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
40
+ | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 11.408 ms | 0 - 365 MB | NPU | Use Export Script |
41
+ | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 10.571 ms | 0 - 20 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
42
+ | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 7.886 ms | 0 - 2 MB | NPU | Use Export Script |
43
+ | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 12.798 ms | 0 - 360 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
44
+ | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 10.059 ms | 0 - 10 MB | NPU | Use Export Script |
45
+ | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 34.455 ms | 105 - 465 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
46
+ | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 29.131 ms | 0 - 9 MB | NPU | Use Export Script |
47
+ | Nomic-Embed-Text | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 10.555 ms | 0 - 19 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
48
+ | Nomic-Embed-Text | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 8.128 ms | 0 - 2 MB | NPU | Use Export Script |
49
+ | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 14.322 ms | 212 - 560 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
50
+ | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 11.224 ms | 0 - 17 MB | NPU | Use Export Script |
51
+ | Nomic-Embed-Text | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 10.547 ms | 0 - 18 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
52
+ | Nomic-Embed-Text | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 8.08 ms | 0 - 2 MB | NPU | Use Export Script |
53
+ | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 12.798 ms | 0 - 360 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
54
+ | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 10.059 ms | 0 - 10 MB | NPU | Use Export Script |
55
+ | Nomic-Embed-Text | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 10.577 ms | 0 - 18 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
56
+ | Nomic-Embed-Text | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 8.023 ms | 0 - 24 MB | NPU | Use Export Script |
57
+ | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 7.591 ms | 0 - 403 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
58
+ | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 5.774 ms | 0 - 367 MB | NPU | Use Export Script |
59
+ | Nomic-Embed-Text | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 7.406 ms | 0 - 362 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
60
+ | Nomic-Embed-Text | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 4.744 ms | 0 - 323 MB | NPU | Use Export Script |
61
+ | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.38 ms | 1 - 1 MB | NPU | Use Export Script |
62
 
63
 
64
 
 
120
  Profiling Results
121
  ------------------------------------------------------------
122
  Nomic-Embed-Text
123
+ Device : cs_8275 (ANDROID 14)
124
+ Runtime : TFLITE
125
+ Estimated inference time (ms) : 34.5
126
+ Estimated peak memory usage (MB): [105, 465]
127
+ Total # Ops : 906
128
+ Compute Unit(s) : npu (906 ops) gpu (0 ops) cpu (0 ops)
129
  ```
130
 
131