version3 upload

README.md

@@ -1,13 +1,13 @@
 ---
 library_name: peft
-base_model: unsloth/gemma-7b-bnb-4bit
+base_model: unsloth/gemma-2-9b-it-bnb-4bit
 language:
 - ja
 - en
 tags:
 - translation
 - qlora
-- gemma
+- gemma2
 - text-generation-inference
 - nlp
 ---
@@ -16,6 +16,17 @@ tags:
 
 # News
 
+## 2024.07.19
+C3TR-AdapterのVersion3を公開しました。  
+Version 3 of C3TR-Adapter has been released.   
+
+このドキュメント等は現在、差し替え作業中で一部古いです。  
+This documentation is currently being replaced and some parts are out of date.  
+
+
+
+
+
 ## 2024.05.17
 C3TR-AdapterのVersion2を公開しました。  
 Version 2 of C3TR-Adapter has been released.  
@@ -546,12 +557,12 @@ Any feedback would be appreciated!
 ### 謝辞 Acknowledgment
 
 Original Base Model  
-google/gemma-7b  
-https://huggingface.co/google/gemma-7b 
+google/gemma-2-9b-it  
+https://huggingface.co/google/gemma-2-9b-it  
 
 Base Model  
 unsloth/gemma-7b-bnb-4bit  
-https://huggingface.co/unsloth/gemma-7b-bnb-4bit
+https://huggingface.co/unsloth/gemma-2-9b-it-bnb-4bit
 
 QLoRA Adapter  
 webbigdata/C3TR-Adapter  

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/gemma-7b-bnb-4bit",
+  "base_model_name_or_path": "unsloth/gemma-2-9b-it-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 64,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "o_proj",
+    "gate_proj",
+    "v_proj",
     "k_proj",
-    "q_proj",
-    "down_proj",
+    "o_proj",
     "up_proj",
-    "gate_proj",
-    "v_proj"
+    "q_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63574dfbad9845da5aaa22aa3344b88855f6e9ab3c33b90b2782bf8cd56bc1a7
-size 800116456
+oid sha256:42eba5d7c8060d980d85c8e100ec5a6d6cbf1a6b044ab784660e0405feca5323
+size 1728658208

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30f819ff5b0f4cef2c8a6aafbeb20a13e7dd14409ece0f1e11e1d84bcfd281b
-size 17518937
+oid sha256:cd1df914b205b134e52f15364524a919423b48c9056d725b45c5b89187541de0
+size 17518965

tokenizer_config.json

@@ -1744,6 +1744,7 @@
     "<end_of_turn>"
   ],
   "bos_token": "<bos>",
+  "chat_template": "{{ 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 + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "model_max_length": 8192,