Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

mlc-chat-config.json

@@ -0,0 +1,99 @@
+{
+  "version": "0.1.0",
+  "model_type": "gemma3",
+  "quantization": "q4bf16_1",
+  "model_config": {
+    "text_config": {
+      "hidden_size": 5376,
+      "intermediate_size": 21504,
+      "num_hidden_layers": 62,
+      "attention_bias": false,
+      "num_attention_heads": 32,
+      "num_key_value_heads": 16,
+      "head_dim": 128,
+      "rms_norm_eps": 1e-06,
+      "hidden_activation": "gelu_pytorch_tanh",
+      "position_embedding_base": 10000,
+      "context_window_size": 8192,
+      "prefill_chunk_size": 8192,
+      "query_pre_attn_scalar": 168,
+      "sliding_window": 1024,
+      "kwargs": {
+        "model_type": "gemma3_text",
+        "rope_scaling": {
+          "factor": 8.0,
+          "rope_type": "linear"
+        }
+      }
+    },
+    "vocab_size": 262208,
+    "tensor_parallel_shards": 1,
+    "max_batch_size": 128,
+    "context_window_size": 8192,
+    "sliding_window_size": -1,
+    "prefill_chunk_size": 8192,
+    "is_text_model": false
+  },
+  "vocab_size": 262208,
+  "context_window_size": 8192,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 8192,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "pipeline_parallel_stages": 1,
+  "temperature": 1.0,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.0,
+  "top_p": 1.0,
+  "tokenizer_files": [
+    "tokenizer.model",
+    "tokenizer.json",
+    "added_tokens.json",
+    "tokenizer_config.json"
+  ],
+  "tokenizer_info": {
+    "token_postproc_method": "byte_fallback",
+    "prepend_space_in_encode": false,
+    "strip_space_in_decode": false
+  },
+  "conv_template": {
+    "name": "gemma_instruction",
+    "system_template": "{system_message}",
+    "system_message": "",
+    "system_prefix_token_ids": [
+      2
+    ],
+    "add_role_after_system_message": true,
+    "roles": {
+      "user": "<start_of_turn>user",
+      "assistant": "<start_of_turn>model"
+    },
+    "role_templates": {
+      "user": "{user_message}",
+      "assistant": "{assistant_message}",
+      "tool": "{tool_message}"
+    },
+    "messages": [],
+    "seps": [
+      "<end_of_turn>\n"
+    ],
+    "role_content_sep": "\n",
+    "role_empty_sep": "\n",
+    "stop_str": [
+      "<end_of_turn>"
+    ],
+    "stop_token_ids": [
+      1,
+      107
+    ],
+    "function_string": "",
+    "use_function_calling": false
+  },
+  "pad_token_id": 0,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    1,
+    106
+  ]
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074