Upload optimized language model w/ WebGPU-compatible GQA (#29)
Browse files- Upload optimized language model w/ WebGPU-compatible GQA (9b303242a8f9d326545b843e1df7034817c2edd3)
- Update config.json (ea0c9de5c48509edf8e2b35059502ff66a17e18f)
- config.json +4 -0
- onnx/decoder_model_merged.onnx +2 -2
- onnx/decoder_model_merged.onnx_data +1 -1
- onnx/decoder_model_merged_bnb4.onnx +2 -2
- onnx/decoder_model_merged_fp16.onnx +2 -2
- onnx/decoder_model_merged_fp16.onnx_data +2 -2
- onnx/decoder_model_merged_int8.onnx +2 -2
- onnx/decoder_model_merged_q4.onnx +2 -2
- onnx/decoder_model_merged_q4f16.onnx +2 -2
- onnx/decoder_model_merged_quantized.onnx +2 -2
- onnx/decoder_model_merged_uint8.onnx +2 -2
config.json
CHANGED
@@ -179,6 +179,10 @@
|
|
179 |
"embed_tokens": "auto",
|
180 |
"vision_encoder": "auto",
|
181 |
"decoder_model_merged": "q4"
|
|
|
|
|
|
|
|
|
182 |
}
|
183 |
},
|
184 |
"use_cache": true,
|
|
|
179 |
"embed_tokens": "auto",
|
180 |
"vision_encoder": "auto",
|
181 |
"decoder_model_merged": "q4"
|
182 |
+
},
|
183 |
+
"use_external_data_format": {
|
184 |
+
"decoder_model_merged.onnx": true,
|
185 |
+
"decoder_model_merged_fp16.onnx": true
|
186 |
}
|
187 |
},
|
188 |
"use_cache": true,
|
onnx/decoder_model_merged.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a5013f7392cb1ab70de86049bdeaf4522599e682e51eeaf1ad22d0ebfffa44
|
3 |
+
size 167944
|
onnx/decoder_model_merged.onnx_data
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6849724416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fc6bd88348afba41dcf8cc1727663cb88a150f3e35c5c011f80a14b48d4a6ec
|
3 |
size 6849724416
|
onnx/decoder_model_merged_bnb4.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e347876c58484dc6c51422ce04265e6054624754f1f8bb9cc7ac6076e55856bf
|
3 |
+
size 967377227
|
onnx/decoder_model_merged_fp16.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec9bfa341a42d5060d69573f5dab1c8be24d9d8cc78af8649c6b077223dcb0c3
|
3 |
+
size 169023
|
onnx/decoder_model_merged_fp16.onnx_data
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cc57156f23eeb36f3a8ed08504b2d050f8d221c1a67dcfc1eea089f93154437
|
3 |
+
size 3424862208
|
onnx/decoder_model_merged_int8.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:861dcec66dc59cd9e7f2622cf28b60917020f23ac43f11ab179893773da5dbda
|
3 |
+
size 1716222232
|
onnx/decoder_model_merged_q4.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e171c9285756185c74ed67e0f598d97bae71d2996f3752fb62dd08db4cbba6
|
3 |
+
size 1074331012
|
onnx/decoder_model_merged_q4f16.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:247de27f420790b553b94b29713c56278aedca18b8d68d63dd2e7d72cca397ef
|
3 |
+
size 965077981
|
onnx/decoder_model_merged_quantized.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9614d219c614af85de470c8870be65e8a3a1d00a8163fb3df8abb6cecb612399
|
3 |
+
size 1716222303
|
onnx/decoder_model_merged_uint8.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9614d219c614af85de470c8870be65e8a3a1d00a8163fb3df8abb6cecb612399
|
3 |
+
size 1716222303
|