Upload folder using huggingface_hub

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: taide/TAIDE-LX-7B-Chat
+base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
 library_name: peft
 ---
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "taide/TAIDE-LX-7B-Chat",
+  "base_model_name_or_path": "MediaTek-Research/Breeze-7B-Instruct-v1_0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "down_proj",
     "up_proj",
-    "k_proj",
     "o_proj",
-    "gate_proj"
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a59409ddf0b672d1655fd2fb81683cc8cc82cfefdca26a7d2e048b432996491
+size 84047370

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<EOD>": 61873,
+  "<PAD>": 61874
+}

special_tokens_map.json

@@ -2,28 +2,28 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5ae3c94ec47bca0ac39941c245df5dfc913feebe2d806bc89365af560e4524
-size 813044
+oid sha256:9298e56c094f0d30431b0e52ad53287f0cadc99ac8ca17cc2144b0eb4753f130
+size 911034

tokenizer_config.json

@@ -6,7 +6,7 @@
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -14,7 +14,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,31 +22,39 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
-      "content": "<pad>",
+    "61873": {
+      "content": "<EOD>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61874": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}\n    {% set loop_messages = messages[1:] %}\n    {% set system_message = messages[0]['content'] %}\n{% else %}\n    {% set loop_messages = messages %}\n    {% set system_message = false %}\n{% endif %}\n{% for message in loop_messages %}\n    {% if loop.index0 == 0 and system_message != false %}\n        {% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}\n    {% else %}\n        {% set content = message['content'] %}\n    {% endif %}\n    {% if message['role'] == 'user' %}\n        {{- bos_token + '[INST] ' + content.strip() + ' [/INST]' -}}\n    {% elif message['role'] == 'system' %}\n        {{- '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' -}}\n    {% elif message['role'] == 'assistant' %}\n        {{- ' '  + content.strip() + ' ' + eos_token -}}\n    {% endif %}\n{% endfor %}\n",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.' %}{% endif %}{{ bos_token }} {{ system_message }} {% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/... or system/user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ ' [INST] ' + message['content'] + ' [/INST] ' }}{% elif message['role'] == 'assistant' %}{{ message['content'] }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "<pad>",
-  "padding_side": "right",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }