Upload folder using huggingface_hub

.gitattributes

@@ -53,3 +53,4 @@ Ministral-8B-Instruct-2410/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=
 Mistral-Nemo-Instruct-2407/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Nemotron-Cascade-8B-Thinking/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Nemotron-Mini-4B-Instruct/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-instruct/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Phi-4-mini-instruct/README.md

@@ -0,0 +1,18 @@
+# Phi-4-mini-instruct
+
+## GenAI WebGPU Model
+
+Generated using `onnxruntime_genai.models.builder`
+
+- **onnxruntime-genai commit**: `41c4ce18fec1240c2f848725e31fbe8854010188`
+- **transformers version**: `4.57.0`
+- **Precision**: int4
+- **Execution Provider**: webgpu
+
+```
+python -m onnxruntime_genai.models.builder -p int4 -e webgpu -m microsoft/Phi-4-mini-instruct -o E:\ai-models\Phi-4-mini-instruct\onnx-webgpu\ --extra_options int4_algo_config=rtn_last int4_is_symmetric=true prune_lm_head=true enable_webgpu_graph=true
+```
+
+## GGUF Model
+
+Downloaded from: [unsloth/Phi-4-mini-instruct-GGUF](https://huggingface.co/unsloth/Phi-4-mini-instruct-GGUF)

Phi-4-mini-instruct/gguf/Phi-4-mini-instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a
+size 2491874272

Phi-4-mini-instruct/onnx-webgpu/added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

Phi-4-mini-instruct/onnx-webgpu/chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% 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 %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}

Phi-4-mini-instruct/onnx-webgpu/genai_config.json

@@ -0,0 +1,60 @@
+{
+  "model": {
+    "bos_token_id": 199999,
+    "context_length": 131072,
+    "decoder": {
+      "session_options": {
+        "log_id": "onnxruntime-genai",
+        "provider_options": [
+          {
+            "webgpu": {
+              "enableGraphCapture": "0",
+              "validationMode": "disabled",
+              "multiRotaryCacheConcatOffset": "4096"
+            }
+          }
+        ]
+      },
+      "filename": "model.onnx",
+      "head_size": 128,
+      "hidden_size": 3072,
+      "inputs": {
+        "input_ids": "input_ids",
+        "attention_mask": "attention_mask",
+        "past_key_names": "past_key_values.%d.key",
+        "past_value_names": "past_key_values.%d.value"
+      },
+      "outputs": {
+        "logits": "logits",
+        "present_key_names": "present.%d.key",
+        "present_value_names": "present.%d.value"
+      },
+      "num_attention_heads": 24,
+      "num_hidden_layers": 32,
+      "num_key_value_heads": 8
+    },
+    "eos_token_id": [
+      200020,
+      199999
+    ],
+    "pad_token_id": 199999,
+    "type": "phi3",
+    "vocab_size": 200064
+  },
+  "search": {
+    "diversity_penalty": 0,
+    "do_sample": false,
+    "early_stopping": true,
+    "length_penalty": 1,
+    "max_length": 131072,
+    "min_length": 0,
+    "no_repeat_ngram_size": 0,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "past_present_share_buffer": true,
+    "repetition_penalty": 1,
+    "temperature": 1,
+    "top_k": 50,
+    "top_p": 1
+  }
+}

Phi-4-mini-instruct/onnx-webgpu/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2e6bc8a269ba9d4a757de89e173936d080b1817cff2b936f148ad478f8f773
+size 240526

Phi-4-mini-instruct/onnx-webgpu/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2f6d1e32ed640665a192438df424507851a780a4ed9bdcc66b0881bd2c0292
+size 2491416576

Phi-4-mini-instruct/onnx-webgpu/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Phi-4-mini-instruct/onnx-webgpu/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
+size 15524095

Phi-4-mini-instruct/onnx-webgpu/tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}