Model update

adapter_config.json

@@ -13,22 +13,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "gate_proj",
     "o_proj",
+    "q_proj",
     "v_proj",
     "k_proj",
-    "gate_proj",
     "down_proj",
     "up_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a60b9d6bd223b7f2f4b0520acb474a7d496d2e210e1fe24f4a8c2149c089cd
-size 166182480
+oid sha256:cac36a378e18d7633646e1854777384570ea9f9bdfc062c834902bf8ef8fac47
+size 83115256

chat_template.jinja

@@ -1,4 +1,8 @@
-{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{'<start_of_turn>user
+' + messages[0]['content'] | trim + ' ' + messages[1]['content'] | trim + '<end_of_turn>
+'}}{% set messages = messages[2:] %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<start_of_turn>user
 ' + message['content'] | trim + '<end_of_turn>
-' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
-'}}{% endif %}
+'}}{% elif message['role'] == 'assistant' %}{{'<start_of_turn>model
+' + message['content'] | trim + '<end_of_turn>
+' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<start_of_turn>model
+' }}{% endif %}

special_tokens_map.json

@@ -1,34 +1,6 @@
 {
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
-  "bos_token": {
-    "content": "<bos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<eos>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<bos>",
+  "eos_token": "<end_of_turn>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ce83119bb404f7f0a6e621b76759d476357dcd01241a90f9ca136ae2b3c11c
+oid sha256:4f4ec9e12434bbdee07008abfb928df9354ad1aee62d988e7bb41e55b989f4e6
 size 34362972

tokenizer_config.json

@@ -11,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<eos>",
+      "content": "<end_of_turn>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -859,7 +859,7 @@
       "special": true
     },
     "107": {
-      "content": "<end_of_turn>",
+      "content": "<eos>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1995,24 +1995,12 @@
       "special": false
     }
   },
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<eos>",
+  "eos_token": "<end_of_turn>",
   "extra_special_tokens": {},
-  "max_length": 8192,
-  "model_max_length": 8192,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "stride": 0,
-  "tokenizer_class": "GemmaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "tokenizer_class": "GemmaTokenizerFast",
+  "unk_token": "<unk>"
 }