Hugging Face's logo

GetSoloTech
/
Medical_Summary_Notes_ONNX

Text Generation
Transformers.js
ONNX
PyTorch
llama
facebook
meta
llama-3
conversational
Model card Files
xet
Community
zeeshaan-ai commited on
Commit
8d8ce9c
·
verified ·
1 Parent(s): 256f0bc

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. onnx/model.onnx +2 -2
  2. onnx/model.onnx_data +1 -1
  3. onnx/model_bnb4.onnx +3 -0
  4. onnx/model_fp16.onnx +2 -2
  5. onnx/model_int8.onnx +3 -0
  6. onnx/model_q4.onnx +3 -0
  7. onnx/model_q4f16.onnx +2 -2
  8. onnx/model_quantized.onnx +2 -2
  9. onnx/model_uint8.onnx +3 -0
  10. quantize_config.json +18 -0
onnx/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78a59dedbf0af47e119483d123f38335a915333339958a127ac9fa3c4883a264
3
- size 723337
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8045cd8bb4b0b596e0beb69f16bb3d1395a1e0db13a439260655526e77eb5fa
3
+ size 529415
onnx/model.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3dfbe83c3a78f1022f0a37bc5a0105b8898b5a4e2c19f679252285d0783866a
3
  size 4943257600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2087ce32caa3b86ab482445f68fce3c63e9c0cecf20c6c42b7fda50e9af35349
3
  size 4943257600
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfddfa9900608026b77b7d2e22b069db5c78be4331264d8105a0359e2dce84b
3
+ size 1598837927
onnx/model_fp16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11770265ab123118f29561f6c304a4e619c5e2a87e90360c36f7bada31b28d96
3
- size 733744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80944ad8c170c2056ad69abde484cadf95a5717051bdce1a96d5af01cdcd92fb
3
+ size 537695
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ec30a9cfc69ef9c5ad781489973659577ec51aeebe51f041b1211d32aef392
3
+ size 1236659605
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7307fb7eedf5bf0e6235f2385908ab93e26a76c676365af17205739757a32d15
3
+ size 1659654471
onnx/model_q4f16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2473a49e8a494e37a05ef731fc3a89f7f4e52caefd31d86222c3895a657effe
3
- size 1073806007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752e0f2b2f35a3ebf30e7464d51e3cc963a3c5fee8a03a6dc389c22541300d9c
3
+ size 1073372836
onnx/model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e51a479b5fd846166c8421f2f4b6189bc874c0ccaf8c027f3238864635b79d8
3
- size 1237121104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ec30a9cfc69ef9c5ad781489973659577ec51aeebe51f041b1211d32aef392
3
+ size 1236659605
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01aca4f30e9593453b74e011f76a2f1a8908ca3605ff540320a56428b74335c3
3
+ size 1236659665
quantize_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modes": [
3
+ "fp16",
4
+ "q8",
5
+ "int8",
6
+ "uint8",
7
+ "q4",
8
+ "q4f16",
9
+ "bnb4"
10
+ ],
11
+ "per_channel": false,
12
+ "reduce_range": false,
13
+ "block_size": null,
14
+ "is_symmetric": true,
15
+ "accuracy_level": null,
16
+ "quant_type": 1,
17
+ "op_block_list": null
18
+ }