Commit
·
2812032
1
Parent(s):
920220c
Upload Phi-4-mini-reasoning ONNX models
Browse files- .gitattributes +2 -1
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json +3 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json +3 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4}/merges.txt +0 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/model.onnx +3 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/model.onnx.data +3 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json +3 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4}/tokenizer.json +0 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json +3 -0
- cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/vocab.json +3 -0
- gpu/gpu-int4-rtn-block-32/added_tokens.json +3 -0
- gpu/gpu-int4-rtn-block-32/genai_config.json +3 -0
- gpu/gpu-int4-rtn-block-32/merges.txt +0 -0
- gpu/gpu-int4-rtn-block-32/model.onnx +3 -0
- gpu/gpu-int4-rtn-block-32/model.onnx.data +3 -0
- gpu/gpu-int4-rtn-block-32/special_tokens_map.json +3 -0
- gpu/gpu-int4-rtn-block-32/tokenizer.json +3 -0
- gpu/gpu-int4-rtn-block-32/tokenizer_config.json +3 -0
- gpu/gpu-int4-rtn-block-32/vocab.json +3 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/LICENSE +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/README.md +0 -0
- npu/qnn-int4/added_tokens.json +3 -0
- npu/qnn-int4/config.json +3 -0
- npu/qnn-int4/genai_config.json +3 -0
- npu/qnn-int4/merges.txt +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_1.bin +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_2.bin +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_3.bin +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_4.bin +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_ctx.onnx_ctx.onnx +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_embeddings.all.quant.onnx +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_iter.onnx_ctx.onnx +0 -0
- {phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_lm_head.all.quant.onnx +0 -0
- npu/qnn-int4/special_tokens_map.json +3 -0
- npu/qnn-int4/tokenizer.json +3 -0
- npu/qnn-int4/tokenizer_config.json +3 -0
- npu/qnn-int4/vocab.json +3 -0
- phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/added_tokens.json +0 -12
- phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/config.json +0 -144
- phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/genai_config.json +0 -391
- phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/special_tokens_map.json +0 -30
- phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/tokenizer_config.json +0 -116
- phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,4 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
-
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.onnx.data filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.json filter=lfs diff=lfs merge=lfs -text
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486
|
| 3 |
+
size 249
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/genai_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fcfa1e663f2bc867f8dc62fae65dd0924f0a4d68b43d1234df742dd19171470
|
| 3 |
+
size 1520
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4}/merges.txt
RENAMED
|
File without changes
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:929ee60b9dfcca848a2c62c6533e18c6e74d9d657e01f577e5b54602c02e5ad5
|
| 3 |
+
size 52119126
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/model.onnx.data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd04a1bdfd475e5909a7a90a948b4fb425b4a565293ec36e34df7ac8c39fe8a4
|
| 3 |
+
size 4856573952
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aff38493227d813e29fcf8406e8e90062f1f031aa47d589325e9c31d89ac7cc3
|
| 3 |
+
size 587
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4}/tokenizer.json
RENAMED
|
File without changes
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16d7cf2abc1139ffc61368dbbacd521d1be29baa30e461382f3bea947cba16ec
|
| 3 |
+
size 3216
|
cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd
|
| 3 |
+
size 3910310
|
gpu/gpu-int4-rtn-block-32/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486
|
| 3 |
+
size 249
|
gpu/gpu-int4-rtn-block-32/genai_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44539bd5e6a1a53e451698216f326b3f030f206ccea77b35ca5a4137df436835
|
| 3 |
+
size 1569
|
gpu/gpu-int4-rtn-block-32/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
gpu/gpu-int4-rtn-block-32/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59ab70c351e50301c1cf4cca3f23176bba73e43f0d94cea26d471ba43b898f65
|
| 3 |
+
size 287586
|
gpu/gpu-int4-rtn-block-32/model.onnx.data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fc3832908b14538d2d53597507a10160e1307c45e153fa5822d82e6248471c3
|
| 3 |
+
size 3413194752
|
gpu/gpu-int4-rtn-block-32/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aff38493227d813e29fcf8406e8e90062f1f031aa47d589325e9c31d89ac7cc3
|
| 3 |
+
size 587
|
gpu/gpu-int4-rtn-block-32/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08ed885956f70d877a4d9078ec9e3119d8b68a8d579003e230be18cad66911c
|
| 3 |
+
size 15524194
|
gpu/gpu-int4-rtn-block-32/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16d7cf2abc1139ffc61368dbbacd521d1be29baa30e461382f3bea947cba16ec
|
| 3 |
+
size 3216
|
gpu/gpu-int4-rtn-block-32/vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd
|
| 3 |
+
size 3910310
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/LICENSE
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/README.md
RENAMED
|
File without changes
|
npu/qnn-int4/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486
|
| 3 |
+
size 249
|
npu/qnn-int4/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac65d86061d3d0d704ee2511fd0eb8713ef19eb6eedba17c3080a4165d5b933b
|
| 3 |
+
size 2504
|
npu/qnn-int4/genai_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cf1863737bcd75cb59c56e8b505ed316132162a47689f85ff52556471dd6698
|
| 3 |
+
size 16942
|
npu/qnn-int4/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_1.bin
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_2.bin
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_3.bin
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_cb_4.bin
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_ctx.onnx_ctx.onnx
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_embeddings.all.quant.onnx
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_iter.onnx_ctx.onnx
RENAMED
|
File without changes
|
{phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx → npu/qnn-int4}/phi_4_mini_lm_head.all.quant.onnx
RENAMED
|
File without changes
|
npu/qnn-int4/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aff38493227d813e29fcf8406e8e90062f1f031aa47d589325e9c31d89ac7cc3
|
| 3 |
+
size 587
|
npu/qnn-int4/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f08ed885956f70d877a4d9078ec9e3119d8b68a8d579003e230be18cad66911c
|
| 3 |
+
size 15524194
|
npu/qnn-int4/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dcb238a84365a07e19dd4334f82da442eea64da30ecbfa3718c06557ea3a589
|
| 3 |
+
size 3323
|
npu/qnn-int4/vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd
|
| 3 |
+
size 3910310
|
phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/added_tokens.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|/tool_call|>": 200026,
|
| 3 |
-
"<|/tool|>": 200024,
|
| 4 |
-
"<|assistant|>": 200019,
|
| 5 |
-
"<|end|>": 200020,
|
| 6 |
-
"<|system|>": 200022,
|
| 7 |
-
"<|tag|>": 200028,
|
| 8 |
-
"<|tool_call|>": 200025,
|
| 9 |
-
"<|tool_response|>": 200027,
|
| 10 |
-
"<|tool|>": 200023,
|
| 11 |
-
"<|user|>": 200021
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/config.json
DELETED
|
@@ -1,144 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "Phi-4-mini-instruct",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"Phi3ForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"auto_map": {
|
| 9 |
-
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
-
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
| 11 |
-
"AutoTokenizer": "Xenova/gpt-4o"
|
| 12 |
-
},
|
| 13 |
-
"bos_token_id": 199999,
|
| 14 |
-
"embd_pdrop": 0.0,
|
| 15 |
-
"eos_token_id": 199999,
|
| 16 |
-
"full_attn_mod": 1,
|
| 17 |
-
"hidden_act": "silu",
|
| 18 |
-
"hidden_size": 3072,
|
| 19 |
-
"initializer_range": 0.02,
|
| 20 |
-
"intermediate_size": 8192,
|
| 21 |
-
"interpolate_factor": 1,
|
| 22 |
-
"lm_head_bias": false,
|
| 23 |
-
"max_position_embeddings": 131072,
|
| 24 |
-
"mlp_bias": false,
|
| 25 |
-
"model_type": "phi3",
|
| 26 |
-
"num_attention_heads": 24,
|
| 27 |
-
"num_hidden_layers": 32,
|
| 28 |
-
"num_key_value_heads": 8,
|
| 29 |
-
"original_max_position_embeddings": 4096,
|
| 30 |
-
"pad_token_id": 199999,
|
| 31 |
-
"partial_rotary_factor": 0.75,
|
| 32 |
-
"resid_pdrop": 0.0,
|
| 33 |
-
"rms_norm_eps": 1e-05,
|
| 34 |
-
"rope_scaling": {
|
| 35 |
-
"long_factor": [
|
| 36 |
-
1,
|
| 37 |
-
1.118320672,
|
| 38 |
-
1.250641126,
|
| 39 |
-
1.398617824,
|
| 40 |
-
1.564103225,
|
| 41 |
-
1.74916897,
|
| 42 |
-
1.956131817,
|
| 43 |
-
2.187582649,
|
| 44 |
-
2.446418898,
|
| 45 |
-
2.735880826,
|
| 46 |
-
3.059592084,
|
| 47 |
-
3.421605075,
|
| 48 |
-
3.826451687,
|
| 49 |
-
4.279200023,
|
| 50 |
-
4.785517845,
|
| 51 |
-
5.351743533,
|
| 52 |
-
5.984965424,
|
| 53 |
-
6.693110555,
|
| 54 |
-
7.485043894,
|
| 55 |
-
8.370679318,
|
| 56 |
-
9.36110372,
|
| 57 |
-
10.4687158,
|
| 58 |
-
11.70738129,
|
| 59 |
-
13.09260651,
|
| 60 |
-
14.64173252,
|
| 61 |
-
16.37415215,
|
| 62 |
-
18.31155283,
|
| 63 |
-
20.47818807,
|
| 64 |
-
22.90118105,
|
| 65 |
-
25.61086418,
|
| 66 |
-
28.64115884,
|
| 67 |
-
32.03,
|
| 68 |
-
32.1,
|
| 69 |
-
32.13,
|
| 70 |
-
32.23,
|
| 71 |
-
32.6,
|
| 72 |
-
32.61,
|
| 73 |
-
32.64,
|
| 74 |
-
32.66,
|
| 75 |
-
32.7,
|
| 76 |
-
32.71,
|
| 77 |
-
32.93,
|
| 78 |
-
32.97,
|
| 79 |
-
33.28,
|
| 80 |
-
33.49,
|
| 81 |
-
33.5,
|
| 82 |
-
44.16,
|
| 83 |
-
47.77
|
| 84 |
-
],
|
| 85 |
-
"short_factor": [
|
| 86 |
-
1.0,
|
| 87 |
-
1.0,
|
| 88 |
-
1.0,
|
| 89 |
-
1.0,
|
| 90 |
-
1.0,
|
| 91 |
-
1.0,
|
| 92 |
-
1.0,
|
| 93 |
-
1.0,
|
| 94 |
-
1.0,
|
| 95 |
-
1.0,
|
| 96 |
-
1.0,
|
| 97 |
-
1.0,
|
| 98 |
-
1.0,
|
| 99 |
-
1.0,
|
| 100 |
-
1.0,
|
| 101 |
-
1.0,
|
| 102 |
-
1.0,
|
| 103 |
-
1.0,
|
| 104 |
-
1.0,
|
| 105 |
-
1.0,
|
| 106 |
-
1.0,
|
| 107 |
-
1.0,
|
| 108 |
-
1.0,
|
| 109 |
-
1.0,
|
| 110 |
-
1.0,
|
| 111 |
-
1.0,
|
| 112 |
-
1.0,
|
| 113 |
-
1.0,
|
| 114 |
-
1.0,
|
| 115 |
-
1.0,
|
| 116 |
-
1.0,
|
| 117 |
-
1.0,
|
| 118 |
-
1.0,
|
| 119 |
-
1.0,
|
| 120 |
-
1.0,
|
| 121 |
-
1.0,
|
| 122 |
-
1.0,
|
| 123 |
-
1.0,
|
| 124 |
-
1.0,
|
| 125 |
-
1.0,
|
| 126 |
-
1.0,
|
| 127 |
-
1.0,
|
| 128 |
-
1.0,
|
| 129 |
-
1.0,
|
| 130 |
-
1.0,
|
| 131 |
-
1.0,
|
| 132 |
-
1.0,
|
| 133 |
-
1.0
|
| 134 |
-
],
|
| 135 |
-
"type": "longrope"
|
| 136 |
-
},
|
| 137 |
-
"rope_theta": 10000.0,
|
| 138 |
-
"sliding_window": 262144,
|
| 139 |
-
"tie_word_embeddings": true,
|
| 140 |
-
"torch_dtype": "bfloat16",
|
| 141 |
-
"transformers_version": "4.45.0",
|
| 142 |
-
"use_cache": true,
|
| 143 |
-
"vocab_size": 200064
|
| 144 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/genai_config.json
DELETED
|
@@ -1,391 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"model": {
|
| 3 |
-
"bos_token_id": 199999,
|
| 4 |
-
"context_length": 4096,
|
| 5 |
-
"decoder": {
|
| 6 |
-
"session_options": {
|
| 7 |
-
"log_id": "onnxruntime-genai",
|
| 8 |
-
"provider_options": []
|
| 9 |
-
},
|
| 10 |
-
"head_size": 128,
|
| 11 |
-
"hidden_size": 3072,
|
| 12 |
-
"inputs": {
|
| 13 |
-
"input_ids": "input_ids",
|
| 14 |
-
"attention_mask": "attention_mask",
|
| 15 |
-
"past_key_names": "past_keys_%d",
|
| 16 |
-
"past_value_names": "past_values_%d",
|
| 17 |
-
"past_sequence_length": "past_seq_len",
|
| 18 |
-
"total_sequence_length": "total_seq_len"
|
| 19 |
-
},
|
| 20 |
-
"outputs": {
|
| 21 |
-
"logits": "logits",
|
| 22 |
-
"present_key_names": "present_keys_%d",
|
| 23 |
-
"present_value_names": "present_values_%d"
|
| 24 |
-
},
|
| 25 |
-
"num_attention_heads": 24,
|
| 26 |
-
"num_hidden_layers": 32,
|
| 27 |
-
"num_key_value_heads": 8,
|
| 28 |
-
"sliding_window": {
|
| 29 |
-
"window_size": 64,
|
| 30 |
-
"pad_value": 0,
|
| 31 |
-
"alignment": "left",
|
| 32 |
-
"slide_key_value_cache": false
|
| 33 |
-
},
|
| 34 |
-
"pipeline": [
|
| 35 |
-
{
|
| 36 |
-
"embedding": {
|
| 37 |
-
"filename": "phi_4_mini_embeddings.all.quant.onnx",
|
| 38 |
-
"inputs": [
|
| 39 |
-
"input_ids"
|
| 40 |
-
],
|
| 41 |
-
"outputs": [
|
| 42 |
-
"input_hidden_states"
|
| 43 |
-
]
|
| 44 |
-
},
|
| 45 |
-
"prompt-processor": {
|
| 46 |
-
"filename": "phi_4_mini_ctx.onnx_ctx.onnx",
|
| 47 |
-
"session_options": {
|
| 48 |
-
"log_id": "onnxruntime-genai.prompt-processor",
|
| 49 |
-
"provider_options": [
|
| 50 |
-
{
|
| 51 |
-
"qnn": {
|
| 52 |
-
"backend_path": "QnnHtp.dll",
|
| 53 |
-
"htp_performance_mode": "burst",
|
| 54 |
-
"htp_graph_finalization_optimization_mode": "3",
|
| 55 |
-
"soc_model": "60"
|
| 56 |
-
}
|
| 57 |
-
}
|
| 58 |
-
],
|
| 59 |
-
"intra_op_num_threads": 12,
|
| 60 |
-
"inter_op_num_threads": 1
|
| 61 |
-
},
|
| 62 |
-
"inputs": [
|
| 63 |
-
"past_keys_0",
|
| 64 |
-
"past_values_0",
|
| 65 |
-
"past_keys_1",
|
| 66 |
-
"past_values_1",
|
| 67 |
-
"past_keys_2",
|
| 68 |
-
"past_values_2",
|
| 69 |
-
"past_keys_3",
|
| 70 |
-
"past_values_3",
|
| 71 |
-
"past_keys_4",
|
| 72 |
-
"past_values_4",
|
| 73 |
-
"past_keys_5",
|
| 74 |
-
"past_values_5",
|
| 75 |
-
"past_keys_6",
|
| 76 |
-
"past_values_6",
|
| 77 |
-
"past_keys_7",
|
| 78 |
-
"past_values_7",
|
| 79 |
-
"past_keys_8",
|
| 80 |
-
"past_values_8",
|
| 81 |
-
"past_keys_9",
|
| 82 |
-
"past_values_9",
|
| 83 |
-
"past_keys_10",
|
| 84 |
-
"past_values_10",
|
| 85 |
-
"past_keys_11",
|
| 86 |
-
"past_values_11",
|
| 87 |
-
"past_keys_12",
|
| 88 |
-
"past_values_12",
|
| 89 |
-
"past_keys_13",
|
| 90 |
-
"past_values_13",
|
| 91 |
-
"past_keys_14",
|
| 92 |
-
"past_values_14",
|
| 93 |
-
"past_keys_15",
|
| 94 |
-
"past_values_15",
|
| 95 |
-
"past_keys_16",
|
| 96 |
-
"past_values_16",
|
| 97 |
-
"past_keys_17",
|
| 98 |
-
"past_values_17",
|
| 99 |
-
"past_keys_18",
|
| 100 |
-
"past_values_18",
|
| 101 |
-
"past_keys_19",
|
| 102 |
-
"past_values_19",
|
| 103 |
-
"past_keys_20",
|
| 104 |
-
"past_values_20",
|
| 105 |
-
"past_keys_21",
|
| 106 |
-
"past_values_21",
|
| 107 |
-
"past_keys_22",
|
| 108 |
-
"past_values_22",
|
| 109 |
-
"past_keys_23",
|
| 110 |
-
"past_values_23",
|
| 111 |
-
"past_keys_24",
|
| 112 |
-
"past_values_24",
|
| 113 |
-
"past_keys_25",
|
| 114 |
-
"past_values_25",
|
| 115 |
-
"past_keys_26",
|
| 116 |
-
"past_values_26",
|
| 117 |
-
"past_keys_27",
|
| 118 |
-
"past_values_27",
|
| 119 |
-
"past_keys_28",
|
| 120 |
-
"past_values_28",
|
| 121 |
-
"past_keys_29",
|
| 122 |
-
"past_values_29",
|
| 123 |
-
"past_keys_30",
|
| 124 |
-
"past_values_30",
|
| 125 |
-
"past_keys_31",
|
| 126 |
-
"past_values_31",
|
| 127 |
-
"input_hidden_states",
|
| 128 |
-
"past_seq_len",
|
| 129 |
-
"total_seq_len"
|
| 130 |
-
],
|
| 131 |
-
"outputs": [
|
| 132 |
-
"output_hidden_states",
|
| 133 |
-
"present_keys_0",
|
| 134 |
-
"present_values_0",
|
| 135 |
-
"present_keys_1",
|
| 136 |
-
"present_values_1",
|
| 137 |
-
"present_keys_2",
|
| 138 |
-
"present_values_2",
|
| 139 |
-
"present_keys_3",
|
| 140 |
-
"present_values_3",
|
| 141 |
-
"present_keys_4",
|
| 142 |
-
"present_values_4",
|
| 143 |
-
"present_keys_5",
|
| 144 |
-
"present_values_5",
|
| 145 |
-
"present_keys_6",
|
| 146 |
-
"present_values_6",
|
| 147 |
-
"present_keys_7",
|
| 148 |
-
"present_values_7",
|
| 149 |
-
"present_keys_8",
|
| 150 |
-
"present_values_8",
|
| 151 |
-
"present_keys_9",
|
| 152 |
-
"present_values_9",
|
| 153 |
-
"present_keys_10",
|
| 154 |
-
"present_values_10",
|
| 155 |
-
"present_keys_11",
|
| 156 |
-
"present_values_11",
|
| 157 |
-
"present_keys_12",
|
| 158 |
-
"present_values_12",
|
| 159 |
-
"present_keys_13",
|
| 160 |
-
"present_values_13",
|
| 161 |
-
"present_keys_14",
|
| 162 |
-
"present_values_14",
|
| 163 |
-
"present_keys_15",
|
| 164 |
-
"present_values_15",
|
| 165 |
-
"present_keys_16",
|
| 166 |
-
"present_values_16",
|
| 167 |
-
"present_keys_17",
|
| 168 |
-
"present_values_17",
|
| 169 |
-
"present_keys_18",
|
| 170 |
-
"present_values_18",
|
| 171 |
-
"present_keys_19",
|
| 172 |
-
"present_values_19",
|
| 173 |
-
"present_keys_20",
|
| 174 |
-
"present_values_20",
|
| 175 |
-
"present_keys_21",
|
| 176 |
-
"present_values_21",
|
| 177 |
-
"present_keys_22",
|
| 178 |
-
"present_values_22",
|
| 179 |
-
"present_keys_23",
|
| 180 |
-
"present_values_23",
|
| 181 |
-
"present_keys_24",
|
| 182 |
-
"present_values_24",
|
| 183 |
-
"present_keys_25",
|
| 184 |
-
"present_values_25",
|
| 185 |
-
"present_keys_26",
|
| 186 |
-
"present_values_26",
|
| 187 |
-
"present_keys_27",
|
| 188 |
-
"present_values_27",
|
| 189 |
-
"present_keys_28",
|
| 190 |
-
"present_values_28",
|
| 191 |
-
"present_keys_29",
|
| 192 |
-
"present_values_29",
|
| 193 |
-
"present_keys_30",
|
| 194 |
-
"present_values_30",
|
| 195 |
-
"present_keys_31",
|
| 196 |
-
"present_values_31"
|
| 197 |
-
],
|
| 198 |
-
"run_on_token_gen": false
|
| 199 |
-
},
|
| 200 |
-
"token-generator": {
|
| 201 |
-
"filename": "phi_4_mini_iter.onnx_ctx.onnx",
|
| 202 |
-
"session_options": {
|
| 203 |
-
"log_id": "onnxruntime-genai.token-generator",
|
| 204 |
-
"provider_options": [
|
| 205 |
-
{
|
| 206 |
-
"qnn": {
|
| 207 |
-
"backend_path": "QnnHtp.dll",
|
| 208 |
-
"htp_performance_mode": "burst",
|
| 209 |
-
"htp_graph_finalization_optimization_mode": "3",
|
| 210 |
-
"soc_model": "60"
|
| 211 |
-
}
|
| 212 |
-
}
|
| 213 |
-
],
|
| 214 |
-
"intra_op_num_threads": 12,
|
| 215 |
-
"inter_op_num_threads": 1
|
| 216 |
-
},
|
| 217 |
-
"inputs": [
|
| 218 |
-
"past_keys_0",
|
| 219 |
-
"past_values_0",
|
| 220 |
-
"past_keys_1",
|
| 221 |
-
"past_values_1",
|
| 222 |
-
"past_keys_2",
|
| 223 |
-
"past_values_2",
|
| 224 |
-
"past_keys_3",
|
| 225 |
-
"past_values_3",
|
| 226 |
-
"past_keys_4",
|
| 227 |
-
"past_values_4",
|
| 228 |
-
"past_keys_5",
|
| 229 |
-
"past_values_5",
|
| 230 |
-
"past_keys_6",
|
| 231 |
-
"past_values_6",
|
| 232 |
-
"past_keys_7",
|
| 233 |
-
"past_values_7",
|
| 234 |
-
"past_keys_8",
|
| 235 |
-
"past_values_8",
|
| 236 |
-
"past_keys_9",
|
| 237 |
-
"past_values_9",
|
| 238 |
-
"past_keys_10",
|
| 239 |
-
"past_values_10",
|
| 240 |
-
"past_keys_11",
|
| 241 |
-
"past_values_11",
|
| 242 |
-
"past_keys_12",
|
| 243 |
-
"past_values_12",
|
| 244 |
-
"past_keys_13",
|
| 245 |
-
"past_values_13",
|
| 246 |
-
"past_keys_14",
|
| 247 |
-
"past_values_14",
|
| 248 |
-
"past_keys_15",
|
| 249 |
-
"past_values_15",
|
| 250 |
-
"past_keys_16",
|
| 251 |
-
"past_values_16",
|
| 252 |
-
"past_keys_17",
|
| 253 |
-
"past_values_17",
|
| 254 |
-
"past_keys_18",
|
| 255 |
-
"past_values_18",
|
| 256 |
-
"past_keys_19",
|
| 257 |
-
"past_values_19",
|
| 258 |
-
"past_keys_20",
|
| 259 |
-
"past_values_20",
|
| 260 |
-
"past_keys_21",
|
| 261 |
-
"past_values_21",
|
| 262 |
-
"past_keys_22",
|
| 263 |
-
"past_values_22",
|
| 264 |
-
"past_keys_23",
|
| 265 |
-
"past_values_23",
|
| 266 |
-
"past_keys_24",
|
| 267 |
-
"past_values_24",
|
| 268 |
-
"past_keys_25",
|
| 269 |
-
"past_values_25",
|
| 270 |
-
"past_keys_26",
|
| 271 |
-
"past_values_26",
|
| 272 |
-
"past_keys_27",
|
| 273 |
-
"past_values_27",
|
| 274 |
-
"past_keys_28",
|
| 275 |
-
"past_values_28",
|
| 276 |
-
"past_keys_29",
|
| 277 |
-
"past_values_29",
|
| 278 |
-
"past_keys_30",
|
| 279 |
-
"past_values_30",
|
| 280 |
-
"past_keys_31",
|
| 281 |
-
"past_values_31",
|
| 282 |
-
"input_hidden_states",
|
| 283 |
-
"past_seq_len",
|
| 284 |
-
"total_seq_len"
|
| 285 |
-
],
|
| 286 |
-
"outputs": [
|
| 287 |
-
"output_hidden_states",
|
| 288 |
-
"present_keys_0",
|
| 289 |
-
"present_values_0",
|
| 290 |
-
"present_keys_1",
|
| 291 |
-
"present_values_1",
|
| 292 |
-
"present_keys_2",
|
| 293 |
-
"present_values_2",
|
| 294 |
-
"present_keys_3",
|
| 295 |
-
"present_values_3",
|
| 296 |
-
"present_keys_4",
|
| 297 |
-
"present_values_4",
|
| 298 |
-
"present_keys_5",
|
| 299 |
-
"present_values_5",
|
| 300 |
-
"present_keys_6",
|
| 301 |
-
"present_values_6",
|
| 302 |
-
"present_keys_7",
|
| 303 |
-
"present_values_7",
|
| 304 |
-
"present_keys_8",
|
| 305 |
-
"present_values_8",
|
| 306 |
-
"present_keys_9",
|
| 307 |
-
"present_values_9",
|
| 308 |
-
"present_keys_10",
|
| 309 |
-
"present_values_10",
|
| 310 |
-
"present_keys_11",
|
| 311 |
-
"present_values_11",
|
| 312 |
-
"present_keys_12",
|
| 313 |
-
"present_values_12",
|
| 314 |
-
"present_keys_13",
|
| 315 |
-
"present_values_13",
|
| 316 |
-
"present_keys_14",
|
| 317 |
-
"present_values_14",
|
| 318 |
-
"present_keys_15",
|
| 319 |
-
"present_values_15",
|
| 320 |
-
"present_keys_16",
|
| 321 |
-
"present_values_16",
|
| 322 |
-
"present_keys_17",
|
| 323 |
-
"present_values_17",
|
| 324 |
-
"present_keys_18",
|
| 325 |
-
"present_values_18",
|
| 326 |
-
"present_keys_19",
|
| 327 |
-
"present_values_19",
|
| 328 |
-
"present_keys_20",
|
| 329 |
-
"present_values_20",
|
| 330 |
-
"present_keys_21",
|
| 331 |
-
"present_values_21",
|
| 332 |
-
"present_keys_22",
|
| 333 |
-
"present_values_22",
|
| 334 |
-
"present_keys_23",
|
| 335 |
-
"present_values_23",
|
| 336 |
-
"present_keys_24",
|
| 337 |
-
"present_values_24",
|
| 338 |
-
"present_keys_25",
|
| 339 |
-
"present_values_25",
|
| 340 |
-
"present_keys_26",
|
| 341 |
-
"present_values_26",
|
| 342 |
-
"present_keys_27",
|
| 343 |
-
"present_values_27",
|
| 344 |
-
"present_keys_28",
|
| 345 |
-
"present_values_28",
|
| 346 |
-
"present_keys_29",
|
| 347 |
-
"present_values_29",
|
| 348 |
-
"present_keys_30",
|
| 349 |
-
"present_values_30",
|
| 350 |
-
"present_keys_31",
|
| 351 |
-
"present_values_31"
|
| 352 |
-
],
|
| 353 |
-
"run_on_prompt": false
|
| 354 |
-
},
|
| 355 |
-
"transformer-head": {
|
| 356 |
-
"filename": "phi_4_mini_lm_head.all.quant.onnx",
|
| 357 |
-
"inputs": [
|
| 358 |
-
"output_hidden_states"
|
| 359 |
-
],
|
| 360 |
-
"outputs": [
|
| 361 |
-
"logits"
|
| 362 |
-
]
|
| 363 |
-
}
|
| 364 |
-
}
|
| 365 |
-
]
|
| 366 |
-
},
|
| 367 |
-
"eos_token_id": [
|
| 368 |
-
200020,
|
| 369 |
-
199999
|
| 370 |
-
],
|
| 371 |
-
"pad_token_id": 199999,
|
| 372 |
-
"type": "decoder-pipeline",
|
| 373 |
-
"vocab_size": 200064
|
| 374 |
-
},
|
| 375 |
-
"search": {
|
| 376 |
-
"diversity_penalty": 0.0,
|
| 377 |
-
"do_sample": true,
|
| 378 |
-
"early_stopping": true,
|
| 379 |
-
"length_penalty": 1.0,
|
| 380 |
-
"max_length": 4096,
|
| 381 |
-
"min_length": 0,
|
| 382 |
-
"no_repeat_ngram_size": 0,
|
| 383 |
-
"num_beams": 1,
|
| 384 |
-
"num_return_sequences": 1,
|
| 385 |
-
"past_present_share_buffer": true,
|
| 386 |
-
"repetition_penalty": 1.0,
|
| 387 |
-
"temperature": 0.6,
|
| 388 |
-
"top_k": 5,
|
| 389 |
-
"top_p": 0.95
|
| 390 |
-
}
|
| 391 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/special_tokens_map.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<|endoftext|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<|endoftext|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "<|endoftext|>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
}
|
| 30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/tokenizer_config.json
DELETED
|
@@ -1,116 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": false,
|
| 5 |
-
"added_tokens_decoder": {
|
| 6 |
-
"199999": {
|
| 7 |
-
"content": "<|endoftext|>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"200018": {
|
| 15 |
-
"content": "<|endofprompt|>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"200019": {
|
| 23 |
-
"content": "<|assistant|>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": true,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
},
|
| 30 |
-
"200020": {
|
| 31 |
-
"content": "<|end|>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": true,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": true
|
| 37 |
-
},
|
| 38 |
-
"200021": {
|
| 39 |
-
"content": "<|user|>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": true,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": true
|
| 45 |
-
},
|
| 46 |
-
"200022": {
|
| 47 |
-
"content": "<|system|>",
|
| 48 |
-
"lstrip": false,
|
| 49 |
-
"normalized": false,
|
| 50 |
-
"rstrip": true,
|
| 51 |
-
"single_word": false,
|
| 52 |
-
"special": true
|
| 53 |
-
},
|
| 54 |
-
"200023": {
|
| 55 |
-
"content": "<|tool|>",
|
| 56 |
-
"lstrip": false,
|
| 57 |
-
"normalized": false,
|
| 58 |
-
"rstrip": true,
|
| 59 |
-
"single_word": false,
|
| 60 |
-
"special": false
|
| 61 |
-
},
|
| 62 |
-
"200024": {
|
| 63 |
-
"content": "<|/tool|>",
|
| 64 |
-
"lstrip": false,
|
| 65 |
-
"normalized": false,
|
| 66 |
-
"rstrip": true,
|
| 67 |
-
"single_word": false,
|
| 68 |
-
"special": false
|
| 69 |
-
},
|
| 70 |
-
"200025": {
|
| 71 |
-
"content": "<|tool_call|>",
|
| 72 |
-
"lstrip": false,
|
| 73 |
-
"normalized": false,
|
| 74 |
-
"rstrip": true,
|
| 75 |
-
"single_word": false,
|
| 76 |
-
"special": false
|
| 77 |
-
},
|
| 78 |
-
"200026": {
|
| 79 |
-
"content": "<|/tool_call|>",
|
| 80 |
-
"lstrip": false,
|
| 81 |
-
"normalized": false,
|
| 82 |
-
"rstrip": true,
|
| 83 |
-
"single_word": false,
|
| 84 |
-
"special": false
|
| 85 |
-
},
|
| 86 |
-
"200027": {
|
| 87 |
-
"content": "<|tool_response|>",
|
| 88 |
-
"lstrip": false,
|
| 89 |
-
"normalized": false,
|
| 90 |
-
"rstrip": true,
|
| 91 |
-
"single_word": false,
|
| 92 |
-
"special": false
|
| 93 |
-
},
|
| 94 |
-
"200028": {
|
| 95 |
-
"content": "<|tag|>",
|
| 96 |
-
"lstrip": false,
|
| 97 |
-
"normalized": false,
|
| 98 |
-
"rstrip": true,
|
| 99 |
-
"single_word": false,
|
| 100 |
-
"special": true
|
| 101 |
-
}
|
| 102 |
-
},
|
| 103 |
-
"bos_token": "<|endoftext|>",
|
| 104 |
-
"chat_template": "{{ '<|system|>Your name is Phi, an AI math expert developed by Microsoft.' }}{% for message in messages %}{% if message['role'] == 'system' %} {{ message['content'] }}{% endif %}{% endfor %}{{ '<|end|>' }}{% for message in messages %}{% if message['role'] != 'system' %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
|
| 105 |
-
"clean_up_tokenization_spaces": false,
|
| 106 |
-
"eos_token": "<|endoftext|>",
|
| 107 |
-
"extra_special_tokens": {},
|
| 108 |
-
"max_length": 1024,
|
| 109 |
-
"model_max_length": 128000,
|
| 110 |
-
"pad_token": "<|endoftext|>",
|
| 111 |
-
"stride": 0,
|
| 112 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 113 |
-
"truncation_side": "right",
|
| 114 |
-
"truncation_strategy": "longest_first",
|
| 115 |
-
"unk_token": "<|endoftext|>"
|
| 116 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
phi-4-mini-reasoning-onnx/phi-4-mini-reasoning-onnx/npu/qnn-phi4-mini-reasoning-onnx/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|