Upload folder using huggingface_hub

.gitattributes

@@ -52,3 +52,4 @@ internlm2_5-7b-chat/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -te
 Ministral-8B-Instruct-2410/onnx-webgpu/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 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

Nemotron-Mini-4B-Instruct/README.md

@@ -0,0 +1,18 @@
+# Nemotron-Mini-4B-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 nvidia/Nemotron-Mini-4B-Instruct -o E:\ai-models\Nemotron-Mini-4B-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/Nemotron-Mini-4B-Instruct-GGUF](https://huggingface.co/bartowski/Nemotron-Mini-4B-Instruct-GGUF)

Nemotron-Mini-4B-Instruct/gguf/Nemotron-Mini-4B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf02846dbd45e9580b9338b90505fb54e00d185713d4b7f06699e2d5d298e48
+size 2697387072

Nemotron-Mini-4B-Instruct/onnx-webgpu/chat_template.jinja

@@ -0,0 +1,15 @@
+{{'<extra_id_0>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{'
+' + message['content'].strip()}}{% if tools or contexts %}{{'
+'}}{% endif %}{% endif %}{% endfor %}{% if tools %}{% for tool in tools %}{{ '
+<tool> ' + tool|tojson + ' </tool>' }}{% endfor %}{% endif %}{% if contexts %}{% if tools %}{{'
+'}}{% endif %}{% for context in contexts %}{{ '
+<context> ' + context.strip() + ' </context>' }}{% endfor %}{% endif %}{{'
+
+'}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<extra_id_1>User
+' + message['content'].strip() + '
+' }}{% elif message['role'] == 'assistant' %}{{ '<extra_id_1>Assistant
+' + message['content'].strip() + '
+' }}{% elif message['role'] == 'tool' %}{{ '<extra_id_1>Tool
+' + message['content'].strip() + '
+' }}{% endif %}{% endfor %}{%- if add_generation_prompt %}{{'<extra_id_1>Assistant
+'}}{%- endif %}

Nemotron-Mini-4B-Instruct/onnx-webgpu/genai_config.json

@@ -0,0 +1,56 @@
+{
+  "model": {
+    "bos_token_id": 2,
+    "context_length": 4096,
+    "decoder": {
+      "session_options": {
+        "log_id": "onnxruntime-genai",
+        "provider_options": [
+          {
+            "webgpu": {
+              "enableGraphCapture": "0",
+              "validationMode": "disabled"
+            }
+          }
+        ]
+      },
+      "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": 3,
+    "pad_token_id": 3,
+    "type": "nemotron",
+    "vocab_size": 256000
+  },
+  "search": {
+    "diversity_penalty": 0,
+    "do_sample": false,
+    "early_stopping": true,
+    "length_penalty": 1,
+    "max_length": 4096,
+    "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
+  }
+}

Nemotron-Mini-4B-Instruct/onnx-webgpu/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2becca11c638013c21c32001302d6bf7e3ea831ed437e8a9d39ad38f86a1da0f
+size 218430

Nemotron-Mini-4B-Instruct/onnx-webgpu/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefe0e1fa2a4a783179e5fa0585344c7a7c995f4a84703e7a0e19db2005d81c2
+size 3882024960

Nemotron-Mini-4B-Instruct/onnx-webgpu/special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Nemotron-Mini-4B-Instruct/onnx-webgpu/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fd32f29cfeb8fee9535681f551697b066992c9d950d810651801be24f39e93
+size 34809710