Upload folder using huggingface_hub

CodeLlama-7b-Instruct-hf/MODEL_INFO.md

@@ -0,0 +1,18 @@
+# CodeLlama-7b-Instruct-hf
+
+## 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 codellama/CodeLlama-7b-Instruct-hf -o E:\ai-models\CodeLlama-7b-Instruct-hf\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/CodeLlama-7B-Instruct-GGUF](https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF)

CodeLlama-7b-Instruct-hf/gguf/codellama-7b-instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0701500c591c2c1b910516658e58044cdfa07b2e8b5a2e3b6808d983441daf1a
+size 4081095360

CodeLlama-7b-Instruct-hf/onnx-webgpu/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}

CodeLlama-7b-Instruct-hf/onnx-webgpu/genai_config.json

@@ -0,0 +1,56 @@
+{
+  "model": {
+    "bos_token_id": 1,
+    "context_length": 16384,
+    "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": 32
+    },
+    "eos_token_id": 2,
+    "pad_token_id": 2,
+    "type": "llama",
+    "vocab_size": 32016
+  },
+  "search": {
+    "diversity_penalty": 0,
+    "do_sample": false,
+    "early_stopping": true,
+    "length_penalty": 1,
+    "max_length": 2048,
+    "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
+  }
+}

CodeLlama-7b-Instruct-hf/onnx-webgpu/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01eac45e97c367fb17b659962561c444f9cf67e381b4d1fbbf4d4440dfed286
+size 241042

CodeLlama-7b-Instruct-hf/onnx-webgpu/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66ec9626c16a4d43491282c01f5312426a94ed67180fd7edea8117a61dae646
+size 4049207296

CodeLlama-7b-Instruct-hf/onnx-webgpu/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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
+  }
+}

CodeLlama-7b-Instruct-hf/onnx-webgpu/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

CodeLlama-7b-Instruct-hf/onnx-webgpu/tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 16384,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}