Upload folder using huggingface_hub

Mistral-7B-Instruct-v0.2/README.md

@@ -0,0 +1,18 @@
+# Mistral-7B-Instruct-v0.2
+
+## 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 mistralai/Mistral-7B-Instruct-v0.2 -o E:\ai-models\Mistral-7B-Instruct-v0.2\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: [TheBloke/Mistral-7B-Instruct-v0.2-GGUF](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF)

Mistral-7B-Instruct-v0.2/gguf/mistral-7b-instruct-v0.2.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0039fd0273fcbebb49228943b17831aadd55cbcbf56f0af00499be2040ccf9
+size 4368439584

Mistral-7B-Instruct-v0.2/onnx-webgpu/chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

Mistral-7B-Instruct-v0.2/onnx-webgpu/genai_config.json

@@ -0,0 +1,56 @@
+{
+  "model": {
+    "bos_token_id": 1,
+    "context_length": 32768,
+    "decoder": {
+      "session_options": {
+        "log_id": "onnxruntime-genai",
+        "provider_options": [
+          {
+            "webgpu": {
+              "enableGraphCapture": "0",
+              "validationMode": "disabled"
+            }
+          }
+        ]
+      },
+      "filename": "model.onnx",
+      "head_size": 128,
+      "hidden_size": 4096,
+      "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": 32,
+      "num_hidden_layers": 32,
+      "num_key_value_heads": 8
+    },
+    "eos_token_id": 2,
+    "pad_token_id": 2,
+    "type": "mistral",
+    "vocab_size": 32000
+  },
+  "search": {
+    "diversity_penalty": 0,
+    "do_sample": false,
+    "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": 1,
+    "top_k": 50,
+    "top_p": 1
+  }
+}

Mistral-7B-Instruct-v0.2/onnx-webgpu/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8ff33538afc424cbfab4c330350b9ed2c90573fcab7cf9b870db3cfc21fb2a
+size 239900

Mistral-7B-Instruct-v0.2/onnx-webgpu/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5d542ef082d0ca68ed67cb9aff2b8402f453af8d793573b611ea487715c0e5
+size 4336254976

Mistral-7B-Instruct-v0.2/onnx-webgpu/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Mistral-7B-Instruct-v0.2/onnx-webgpu/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

Mistral-7B-Instruct-v0.2/onnx-webgpu/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}