Upload folder using huggingface_hub

.gitattributes

@@ -55,3 +55,4 @@ Nemotron-Cascade-8B-Thinking/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merg
 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-reasoning/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2-0.5B-Instruct/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen2-0.5B-Instruct/README.md

@@ -0,0 +1,18 @@
+# Qwen2-0.5B-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 Qwen/Qwen2-0.5B-Instruct -o E:\ai-models\Qwen2-0.5B-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: [bartowski/Qwen2.5-0.5B-Instruct-GGUF](https://huggingface.co/bartowski/Qwen2.5-0.5B-Instruct-GGUF)

Qwen2-0.5B-Instruct/gguf/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb923e7d26e9cea28811e1a8e852009b21242fb157b26149d3b188f3a8c8653
+size 397808192

Qwen2-0.5B-Instruct/onnx-webgpu/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

Qwen2-0.5B-Instruct/onnx-webgpu/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

Qwen2-0.5B-Instruct/onnx-webgpu/genai_config.json

@@ -0,0 +1,59 @@
+{
+  "model": {
+    "bos_token_id": 151643,
+    "context_length": 32768,
+    "decoder": {
+      "session_options": {
+        "log_id": "onnxruntime-genai",
+        "provider_options": [
+          {
+            "webgpu": {
+              "enableGraphCapture": "0",
+              "validationMode": "disabled"
+            }
+          }
+        ]
+      },
+      "filename": "model.onnx",
+      "head_size": 64,
+      "hidden_size": 896,
+      "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": 14,
+      "num_hidden_layers": 24,
+      "num_key_value_heads": 2
+    },
+    "eos_token_id": [
+      151645,
+      151643
+    ],
+    "pad_token_id": 151643,
+    "type": "qwen2",
+    "vocab_size": 151936
+  },
+  "search": {
+    "diversity_penalty": 0,
+    "do_sample": true,
+    "early_stopping": true,
+    "length_penalty": 1,
+    "max_length": 32768,
+    "min_length": 0,
+    "no_repeat_ngram_size": 0,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "past_present_share_buffer": true,
+    "repetition_penalty": 1,
+    "temperature": 0.7,
+    "top_k": 20,
+    "top_p": 0.8
+  }
+}

Qwen2-0.5B-Instruct/onnx-webgpu/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e4b5626d0400d2b0960ab742f2a7c76e5b04f53cfa76a5697c46845a1481e1
+size 190215

Qwen2-0.5B-Instruct/onnx-webgpu/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb5072b94ce99885b6e7112db146c5c6910e31a4f725d7983bb2d42c57bed38
+size 353845248

Qwen2-0.5B-Instruct/onnx-webgpu/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Qwen2-0.5B-Instruct/onnx-webgpu/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

Qwen2-0.5B-Instruct/onnx-webgpu/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}