Upload optimized ONNX model

.gitattributes

@@ -33,3 +33,5 @@ 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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -55,5 +55,15 @@
   "use_cla": false,
   "use_qk_norm": true,
   "use_rotary_pos_emb": true,
-  "vocab_size": 120818
-}
+  "vocab_size": 120818,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": 1,
+      "model_fp16.onnx": 1
+    },
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    }
+  }
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b76af2c1be9520fd960b773e65346d805b4783f5ce225196a056f6249743cd
+size 23933

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ee96150cd3721466c67ab251310f01334c0c006ce67489eada47f7756c546f
+size 48001536

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5244d92f8675934a3c68f56ed157f092554bcd349bb46eff612ed95fe78d128
+size 23399

onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f4fa048f1f4e0d8a8902208c4b8d1d175dd8311a689a251578fd616c3bf9c6
+size 24000768

tokenizer_config.json

@@ -1,11 +1,12 @@
 {
   "backend": "tokenizers",
-  "bos_token": "<｜hy_begin▁of▁sentence｜>",
+  "bos_token": "<\uff5chy_begin\u2581of\u2581sentence\uff5c>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<｜hy_place▁holder▁no▁2｜>",
+  "eos_token": "<\uff5chy_place\u2581holder\u2581no\u25812\uff5c>",
   "is_local": false,
   "model_max_length": 1000000000000000019884624838656,
   "model_specific_special_tokens": {},
-  "pad_token": "<｜hy_▁pad▁｜>",
-  "tokenizer_class": "TokenizersBackend"
-}
+  "pad_token": "<\uff5chy_\u2581pad\u2581\uff5c>",
+  "tokenizer_class": "TokenizersBackend",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}<\uff5chy_begin\u2581of\u2581sentence\uff5c>{{ system_message }}<\uff5chy_place\u2581holder\u2581no\u25813\uff5c>{% else %}{% set loop_messages = messages %}<\uff5chy_begin\u2581of\u2581sentence\uff5c>{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}<\uff5chy_User\uff5c>{{ message['content'] }}{% elif message['role'] == 'assistant' %}<\uff5chy_Assistant\uff5c>{{ message['content'] }}<\uff5chy_place\u2581holder\u2581no\u25812\uff5c>{% endif %}{% endfor %}{% if add_generation_prompt %}<\uff5chy_Assistant\uff5c>{% else %}<\uff5chy_place\u2581holder\u2581no\u25818\uff5c>{% endif %}"
+}