qaihm-bot commited on
Commit
6764a2a
·
verified ·
1 Parent(s): b6d24cf

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Nomic-Embed-Text_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3609962b5a1ccecf96381adff220aed7ab601cc9016b8b5e19eaaf89192ef164
3
- size 547931588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b6f2c9cb7b7f277b41ad88a7a5046fe96f4664e857e13f31576379772d1740
3
+ size 547931668
Nomic-Embed-Text_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f2e5adfa1680b7875a9ac658858e1e2a6469acf40fc39bf7bb444824e965d29
3
- size 507492854
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0555940c0b340fb7299627fddd7f91f6cc09254f904a36814f6e894ea135c6f6
3
+ size 507492819
README.md CHANGED
@@ -35,36 +35,33 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 31.651 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
39
- | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 28.229 ms | 0 - 361 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
40
- | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 10.867 ms | 0 - 372 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
41
- | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 10.793 ms | 0 - 371 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
42
- | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 8.779 ms | 0 - 15 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
43
- | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.471 ms | 0 - 23 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
44
- | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.243 ms | 0 - 20 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
45
- | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.131 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
46
- | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.679 ms | 0 - 363 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
47
- | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 31.651 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
48
- | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 28.229 ms | 0 - 361 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
49
- | Nomic-Embed-Text | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 8.813 ms | 3 - 29 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
50
- | Nomic-Embed-Text | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 7.441 ms | 0 - 26 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
51
- | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 12.375 ms | 0 - 358 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
52
- | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 10.565 ms | 0 - 356 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
53
- | Nomic-Embed-Text | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 8.839 ms | 0 - 15 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
54
- | Nomic-Embed-Text | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 7.473 ms | 0 - 27 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
55
- | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 11.131 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
56
- | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 9.679 ms | 0 - 363 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
57
- | Nomic-Embed-Text | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 8.77 ms | 0 - 15 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 S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 7.437 ms | 0 - 28 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
59
- | Nomic-Embed-Text | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 8.331 ms | 0 - 25 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
60
- | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 6.405 ms | 0 - 370 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
61
- | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.324 ms | 0 - 372 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
62
- | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.777 ms | 0 - 369 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
63
- | Nomic-Embed-Text | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 6.247 ms | 0 - 365 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
64
- | Nomic-Embed-Text | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.186 ms | 0 - 365 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
65
- | Nomic-Embed-Text | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.446 ms | 0 - 362 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
66
- | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.027 ms | 1501 - 1501 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
67
- | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.661 ms | 264 - 264 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
68
 
69
 
70
 
@@ -146,7 +143,7 @@ from qai_hub_models.models.nomic_embed_text import Model
146
  torch_model = Model.from_pretrained()
147
 
148
  # Device
149
- device = hub.Device("Samsung Galaxy S24")
150
 
151
  # Trace model
152
  input_shape = torch_model.get_input_spec()
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 31.662 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
39
+ | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 28.132 ms | 0 - 363 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
40
+ | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 10.782 ms | 0 - 370 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
41
+ | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 10.733 ms | 0 - 368 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
42
+ | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 8.729 ms | 0 - 48 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
43
+ | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.425 ms | 0 - 27 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
44
+ | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.314 ms | 0 - 22 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
45
+ | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.164 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
46
+ | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.595 ms | 23 - 385 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
47
+ | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 31.662 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
48
+ | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 28.132 ms | 0 - 363 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
49
+ | Nomic-Embed-Text | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 9.006 ms | 0 - 16 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
50
+ | Nomic-Embed-Text | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 7.425 ms | 0 - 29 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
51
+ | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 12.548 ms | 0 - 357 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
52
+ | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 10.701 ms | 0 - 356 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
53
+ | Nomic-Embed-Text | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 9.019 ms | 0 - 17 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
54
+ | Nomic-Embed-Text | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 7.41 ms | 0 - 27 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
55
+ | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 11.164 ms | 0 - 364 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
56
+ | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 9.595 ms | 23 - 385 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
57
+ | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 6.423 ms | 0 - 369 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_DLC | 5.276 ms | 0 - 370 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
59
+ | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.785 ms | 35 - 409 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
60
+ | Nomic-Embed-Text | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 5.327 ms | 0 - 366 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
61
+ | Nomic-Embed-Text | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 4.177 ms | 0 - 365 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
62
+ | Nomic-Embed-Text | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.587 ms | 0 - 366 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
63
+ | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.02 ms | 1513 - 1513 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
64
+ | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.659 ms | 263 - 263 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
 
 
 
65
 
66
 
67
 
 
143
  torch_model = Model.from_pretrained()
144
 
145
  # Device
146
+ device = hub.Device("Samsung Galaxy S25")
147
 
148
  # Trace model
149
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-snapdragon-x-elite/Nomic-Embed-Text_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e105570495a96e247bea98dd756d7db477b44ed4cb28cc4a2beaedbc6a26469
3
- size 274829312
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/Nomic-Embed-Text_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aadbf235a5ac75d45ace78cf110584a6a449247b3ee288c2ad29c9b2d5bd0a0
3
- size 253752873
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- precompiled_qnn_onnx:
3
- qairt: 2.36.4.250725200057_123280
 
 
 
 
tool-versions.yaml CHANGED
@@ -1,4 +1,4 @@
1
  tool_versions:
2
  onnx:
3
- qairt: 2.36.4.250725200057_123280
4
- onnx_runtime: 1.22.0
 
1
  tool_versions:
2
  onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
+ onnx_runtime: 1.22.2