add template, modify datasets

Former-commit-id: 386f590209e466b51c17a7ac8cee55fc3ce928d7

data/belle_multiturn/belle_multiturn.py

@@ -1,6 +1,5 @@
 import json
 import datasets
-from typing import Any, Dict, List
 
 
 _DESCRIPTION = "BELLE multiturn chat dataset."
@@ -23,7 +22,7 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
 
     VERSION = datasets.Version("0.0.0")
 
-    def _info(self) -> datasets.DatasetInfo:
+    def _info(self):
         features = datasets.Features({
             "instruction": datasets.Value("string"),
             "output": datasets.Value("string"),
@@ -37,7 +36,7 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
             citation=_CITATION
         )
 
-    def _split_generators(self, dl_manager: datasets.DownloadManager) -> List[datasets.SplitGenerator]:
+    def _split_generators(self, dl_manager: datasets.DownloadManager):
         file_path = dl_manager.download(_URL)
         return [
             datasets.SplitGenerator(
@@ -48,7 +47,7 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
             )
         ]
 
-    def _generate_examples(self, filepath: str) -> Dict[int, Dict[str, Any]]: # generate multi-turn chat with history
+    def _generate_examples(self, filepath: str):
         with open(filepath, "r", encoding="utf-8") as f:
             for key, row in enumerate(f):
                 data = json.loads(row)

data/dataset_info.json

@@ -96,11 +96,7 @@
   },
   "ultra_chat": {
     "script_url": "ultra_chat",
-    "columns": {
+    "formatting": "sharegpt"
-      "prompt": "instruction",
-      "response": "output",
-      "history": "history"
-    }
   },
   "open_platypus": {
     "hf_hub_url": "garage-bAInd/Open-Platypus"

data/example_dataset/example_dataset.py

@@ -3,7 +3,7 @@ import datasets
 from typing import Any, Dict, List
 
 
-_DESCRIPTION = "An example of dataset for LLaMA."
+_DESCRIPTION = "An example of dataset."
 _CITATION = ""
 _HOMEPAGE = ""
 _LICENSE = ""

data/hh_rlhf_en/hh_rlhf_en.py

@@ -1,9 +1,9 @@
 import json
 import datasets
-from typing import Any, Dict, List
+from typing import List
 
 
-_DESCRIPTION = "Human preference data about helpfulness and harmlessness for ChatGLM."
+_DESCRIPTION = "Human preference data about helpfulness and harmlessness."
 _CITATION = ""
 _HOMEPAGE = "https://huggingface.co/datasets/Anthropic/hh-rlhf"
 _LICENSE = "mit"
@@ -42,7 +42,7 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
             citation=_CITATION
         )
 
-    def _split_generators(self, dl_manager: datasets.DownloadManager) -> List[datasets.SplitGenerator]:
+    def _split_generators(self, dl_manager: datasets.DownloadManager):
         file_path = dl_manager.download_and_extract(_URLS)
         return [
             datasets.SplitGenerator(
@@ -59,7 +59,7 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
             )
         ]
 
-    def _generate_examples(self, filepaths: List[str]) -> Dict[int, Dict[str, Any]]: # generate multi-turn chat for ChatGLM
+    def _generate_examples(self, filepaths: List[str]):
         key = 0
         for filepath in filepaths:
             with open(filepath, "r", encoding="utf-8") as f:

data/ultra_chat/ultra_chat.py

@@ -1,6 +1,6 @@
 import json
 import datasets
-from typing import Any, Dict, List
+from typing import List
 
 
 _DESCRIPTION = "UltraChat: Large-scale, Informative, and Diverse Multi-round Dialogue Data."
@@ -21,15 +21,13 @@ _LICENSE = "cc-by-nc-4.0"
 _BASE_DATA_URL = "https://huggingface.co/datasets/stingning/ultrachat/resolve/main/train_{idx}.jsonl"
 
 
-class BelleMultiturn(datasets.GeneratorBasedBuilder):
+class UltraChat(datasets.GeneratorBasedBuilder):
 
     VERSION = datasets.Version("0.0.0")
 
-    def _info(self) -> datasets.DatasetInfo:
+    def _info(self):
         features = datasets.Features({
-            "instruction": datasets.Value("string"),
+            "conversations": [{"from": datasets.Value("string"), "value": datasets.Value("string")}]
-            "output": datasets.Value("string"),
-            "history": datasets.Sequence(datasets.Sequence(datasets.Value("string")))
         })
         return datasets.DatasetInfo(
             description=_DESCRIPTION,
@@ -39,8 +37,8 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
             citation=_CITATION
         )
 
-    def _split_generators(self, dl_manager: datasets.DownloadManager) -> List[datasets.SplitGenerator]:
+    def _split_generators(self, dl_manager: datasets.DownloadManager):
-        file_paths = [dl_manager.download(_BASE_DATA_URL.format(idx=idx)) for idx in range(9)] # multiple shards
+        file_paths = [dl_manager.download(_BASE_DATA_URL.format(idx=idx)) for idx in range(10)] # multiple shards
         return [
             datasets.SplitGenerator(
                 name=datasets.Split.TRAIN,
@@ -50,7 +48,7 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
             )
         ]
 
-    def _generate_examples(self, filepaths: List[str]) -> Dict[int, Dict[str, Any]]: # generate multi-turn chat for ChatGLM
+    def _generate_examples(self, filepaths: List[str]):
         for filepath in filepaths:
             with open(filepath, "r", encoding="utf-8") as f:
                 for row in f:
@@ -58,19 +56,16 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
                         data = json.loads(row)
                     except:
                         continue
-                    key = data["id"]
+                    key: int = data["id"]
-                    content = data["data"]
+                    content: List[str] = data["data"]
                     if len(content) % 2 == 1:
                         content.pop(-1)
                     if len(content) < 2:
                         continue
-
+                    conversations = [{
-                    query = content[-2]
+                        "from": "human" if i % 2 == 0 else "gpt",
-                    response = content[-1]
+                        "value": content[i]
-                    history = [[content[2*i], content[2*i+1]] for i in range(len(content) // 2 - 1)]
+                    } for i in range(len(content))]
-
                     yield key, {
-                        "instruction": query,
+                        "conversations": conversations
-                        "output": response,
-                        "history": history
                     }

src/llmtuner/dsets/preprocess.py

@@ -51,9 +51,6 @@ def preprocess_dataset(
             setattr(tokenizer, "add_eos_token", True)
 
         tokenized_examples = tokenizer(examples["prompt"], **kwargs)
-        # Make sure the saved tokenizer is the same as the original
-        if hasattr(tokenizer, "add_eos_token"):  # for Baichuan2 tokenizer
-            setattr(tokenizer, "add_eos_token", add_eos_token_flag)
         concatenated_examples = {k: list(chain(*tokenized_examples[k])) for k in tokenized_examples.keys()}
         total_length = len(concatenated_examples[list(concatenated_examples.keys())[0]])
         block_size = data_args.cutoff_len
@@ -64,6 +61,9 @@ def preprocess_dataset(
             k: [t[i: i + block_size] for i in range(0, total_length, block_size)]
             for k, t in concatenated_examples.items()
         }
+        # make sure the saved tokenizer is the same as the original one
+        if hasattr(tokenizer, "add_eos_token"):
+            setattr(tokenizer, "add_eos_token", add_eos_token_flag)
         return result
 
     def preprocess_supervised_dataset(examples: Dict[str, List[Any]]) -> Dict[str, List[List[int]]]:

src/llmtuner/extras/template.py

@@ -546,7 +546,7 @@ register_template(
         {"token": "<|end_of_turn|>"},
         "GPT4 Correct Assistant:"
     ],
-    system="You are a helpful assistant.",
+    system="",
     sep=[
         {"token": "<|end_of_turn|>"}
     ],
@@ -668,6 +668,43 @@ register_template(
 )
 
 
+r"""
+Supports: https://huggingface.co/wenge-research/yayi-7b
+          https://huggingface.co/wenge-research/yayi-7b-llama2
+          https://huggingface.co/wenge-research/yayi-13b-llama2
+"""
+register_template(
+    name="yayi",
+    prefix=[
+        {"token": "<|System|>"},
+        ":\n{{system}}"
+    ],
+    prompt=[
+        {"token": "<|Human|>"},
+        ":\n{{query}}\n\n",
+        {"token": "<|YaYi|>"},
+        ":"
+    ],
+    system=(
+        "You are a helpful, respectful and honest assistant named YaYi "
+        "developed by Beijing Wenge Technology Co.,Ltd. "
+        "Always answer as helpfully as possible, while being safe.  "
+        "Your answers should not include any harmful, unethical, "
+        "racist, sexist, toxic, dangerous, or illegal content. "
+        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
+        "If a question does not make any sense, or is not factually coherent, "
+        "explain why instead of answering something not correct. "
+        "If you don't know the answer to a question, please don't share false information."
+    ),
+    sep=[
+        "\n\n"
+    ],
+    stop_words=[
+        "<|End|>"
+    ]
+)
+
+
 r"""
 Supports: https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
           https://huggingface.co/HuggingFaceH4/zephyr-7b-beta