tweak to make it work when we have no explicit test split

update pip install command for apex

.github/workflows/base.yml

@@ -26,7 +26,7 @@ jobs:
             pytorch: 2.0.0
             axolotl_extras:
           - cuda: "117"
-            cuda_version: 11.7.0
+            cuda_version: 11.7.1
             python_version: "3.9"
             pytorch: 1.13.1
             axolotl_extras:

.github/workflows/main.yml

@@ -30,7 +30,7 @@ jobs:
             pytorch: 2.0.0
             axolotl_extras: gptq
           - cuda: cu117
-            cuda_version: 11.7.0
+            cuda_version: 11.7.1
             python_version: "3.9"
             pytorch: 1.13.1
             axolotl_extras:
@@ -85,7 +85,7 @@ jobs:
             pytorch: 2.0.0
             axolotl_extras: gptq
           - cuda: cu117
-            cuda_version: 11.7.0
+            cuda_version: 11.7.1
             python_version: "3.9"
             pytorch: 1.13.1
             axolotl_extras:

.pre-commit-config.yaml

@@ -1,5 +1,5 @@
 default_language_version:
-    python: python3.9
+    python: python3
 
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks

README.md

@@ -195,6 +195,10 @@ Have dataset(s) in one of the following format (JSONL recommended):
   ```json
   {"message_1": "...", "message_2": "..."}
   ```
+- `alpaca_w_system.load_open_orca`: support for open orca datasets with included system prompts, instruct
+  ```json
+  {"system_prompt": "...", "question": "...", "response": "..."}
+  ```
 - `context_qa`: in context question answering from an article
   ```json
   {"article": "...", "question": "...", "answer": "..."}
@@ -302,6 +306,8 @@ model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
 # Trust remote code for untrusted source
 trust_remote_code:
+# use_fast option for tokenizer loading from_pretrained, default to True
+tokenizer_use_fast:
 
 # whether you are training a 4-bit GPTQ quantized model
 gptq: true
@@ -334,6 +340,8 @@ datasets:
 dataset_prepared_path: data/last_run_prepared
 # push prepared dataset to hub
 push_dataset_to_hub: # repo path
+# push checkpoints to hub
+push_to_hub_model_id: # repo path
 # whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
 # required to be true when used in combination with `push_dataset_to_hub`
 hf_use_auth_token: # boolean

docker/Dockerfile-base

@@ -77,7 +77,7 @@ FROM base-builder
 RUN python3 -m pip uninstall -y apex
 RUN git clone https://github.com/NVIDIA/apex
 #  `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
-RUN cd apex && MAX_JOBS=1 python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
+RUN cd apex && MAX_JOBS=1 python3 -m pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
 
 RUN mkdir -p /workspace/builds
 COPY --from=bnb-builder /workspace/bitsandbytes /workspace/builds/bitsandbytes

src/axolotl/datasets.py

@@ -126,6 +126,7 @@ class ConstantLengthDataset(IterableDataset):
                     buffer_len = 0
 
                 if example:
+                    # FIXME
                     # just going to drop data points that are too long
                     if len(example["input_ids"]) <= self.seq_length:
                         input_ids = example["input_ids"]

src/axolotl/prompt_strategies/alpaca_chat.py

@@ -6,7 +6,7 @@ from axolotl.prompt_tokenizers import (
     AlpacaPromptTokenizingStrategy,
     InstructionPromptTokenizingStrategy,
 )
-from axolotl.prompters import AlpacaPrompter, PromptStyle
+from axolotl.prompters import AlpacaPrompter, PromptStyle, UnpromptedPrompter
 
 
 def load(tokenizer, cfg):
@@ -45,8 +45,10 @@ class NoSystemPrompter(AlpacaPrompter):
     Null Prompter with no system prompts
     """
 
-    prompt_input = "{instruction} {input} "
+    system_prompt = ""
-    prompt_no_input = "{instruction} "
+    system_no_input_prompt = ""
+    turn_format = "{instruction} {input} "
+    turn_no_input_format = "{instruction} "
 
     def __init__(self):  # pylint: disable=super-init-not-called
         pass
@@ -103,3 +105,12 @@ def load_camel_ai(tokenizer, cfg):
         cfg.train_on_inputs,
         cfg.sequence_len,
     )
+
+
+def load_no_prompt(tokenizer, cfg):
+    return AlpacaPromptTokenizingStrategy(
+        UnpromptedPrompter(PromptStyle.CHAT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )

src/axolotl/prompt_strategies/alpaca_instruct.py

@@ -1,7 +1,7 @@
 """Module loading the AlpacaInstructPromptTokenizingStrategy class"""
 
 from axolotl.prompt_tokenizers import AlpacaPromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter, PromptStyle
+from axolotl.prompters import AlpacaPrompter, PromptStyle, UnpromptedPrompter
 
 
 def load(tokenizer, cfg):
@@ -11,3 +11,12 @@ def load(tokenizer, cfg):
         cfg.train_on_inputs,
         cfg.sequence_len,
     )
+
+
+def load_no_prompt(tokenizer, cfg):
+    return AlpacaPromptTokenizingStrategy(
+        UnpromptedPrompter(PromptStyle.INSTRUCT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )

src/axolotl/prompt_strategies/alpaca_w_system.py

@@ -0,0 +1,120 @@
+"""
+Prompt strategies loader for alpaca instruction datasets with system prompts
+"""
+from typing import Generator, Tuple, Union
+
+from axolotl.prompt_tokenizers import PromptTokenizingStrategy
+from axolotl.prompters import AlpacaPrompter, PromptStyle
+
+
+class InstructionWSystemPromptTokenizingStrategy(PromptTokenizingStrategy):
+    """
+    Tokenizing strategy for instruction-based prompts.
+    """
+
+    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str, str]:
+        return (
+            prompt["instruction"],
+            prompt["input"] if "input" in prompt else "",
+            prompt["output"],
+            prompt["system"],
+        )
+
+    def tokenize_prompt(self, prompt):
+        # pylint: disable=duplicate-code
+        (
+            instruction,
+            input,  # pylint: disable=redefined-builtin
+            response,
+            system,
+        ) = self.parse_instruction_fields(prompt)
+        user_prompt = next(
+            iter(
+                self.prompter.build_prompt_w_system(
+                    system,
+                    instruction,
+                    input,
+                )
+            )
+        )
+        tokenized_prompt = self._tokenize(user_prompt, add_eos_token=False)
+        if not self.train_on_inputs:
+            user_prompt_len = len(tokenized_prompt["input_ids"])
+            # TODO this could be sped up using numpy array slicing
+            tokenized_prompt["labels"] = [-100] * user_prompt_len
+        tokenized_res_prompt = self._tokenize(
+            response, strip_bos_token=True, add_eos_token=True
+        )
+        tokenized_prompt["input_ids"] += tokenized_res_prompt["input_ids"]
+        tokenized_prompt["attention_mask"] += tokenized_res_prompt["attention_mask"]
+        tokenized_prompt["labels"] += tokenized_res_prompt["input_ids"]
+
+        return tokenized_prompt
+
+
+class SystemDataPrompter(AlpacaPrompter):
+    """
+    Alpaca Style Prompter that uses system prompts from the dataset
+    """
+
+    def build_prompt_w_system(
+        self,
+        system: str,
+        instruction: str,
+        input: Union[None, str] = None,  # pylint: disable=redefined-builtin
+        output: Union[None, str] = None,
+    ) -> Generator[str, None, None]:
+        # returns the full prompt from instruction and optional input
+        # if a label (=response, =output) is provided, it's also appended.
+        if input:
+            res = system + self.turn_format.format(instruction=instruction, input=input)
+        else:
+            res = system + self.turn_no_input_format.format(instruction=instruction)
+        if output:
+            res = f"{res}{output}"
+        yield res
+
+
+class OpenOrcaPromptTokenizingStrategy(InstructionWSystemPromptTokenizingStrategy):
+    """
+    Tokenizing strategy for OpenOrca datasets
+    """
+
+    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str, str]:
+        return (
+            prompt["question"],
+            "",
+            prompt["response"],
+            prompt["system_prompt"],
+        )
+
+
+def load(tokenizer, cfg):
+    return load_chat(tokenizer, cfg)
+
+
+def load_instruct(tokenizer, cfg):
+    return InstructionWSystemPromptTokenizingStrategy(
+        SystemDataPrompter(PromptStyle.INSTRUCT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )
+
+
+def load_chat(tokenizer, cfg):
+    return InstructionWSystemPromptTokenizingStrategy(
+        SystemDataPrompter(PromptStyle.CHAT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )
+
+
+def load_open_orca(tokenizer, cfg):
+    return OpenOrcaPromptTokenizingStrategy(
+        SystemDataPrompter(PromptStyle.INSTRUCT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )

src/axolotl/prompt_tokenizers.py

@@ -87,7 +87,9 @@ class InstructionPromptTokenizingStrategy(PromptTokenizingStrategy):
     Tokenizing strategy for instruction-based prompts.
     """
 
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
+    def parse_instruction_fields(
+        self, prompt
+    ) -> Union[Tuple[str, str, str], Tuple[str, str, str, str]]:
         raise NotImplementedError
 
     def tokenize_prompt(self, prompt):
@@ -438,7 +440,7 @@ def parse_tokenized_to_result(
     result: Dict[str, List[int]],
     current_len: int,
     res: Dict[str, List[int]],
-    labels: list[int],
+    labels: List[int],
     pad_token_id: Union[int, None] = None,
 ) -> Tuple[Dict[str, List[int]], int]:
     """

src/axolotl/prompters.py

@@ -24,6 +24,8 @@ class AlpacaPrompter:
 
     system_prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n"
     system_no_input_prompt = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n"
+    turn_format: str
+    turn_no_input_format: str
     prompt_style: Optional[PromptStyle] = None
 
     def __init__(self, prompt_style=PromptStyle.INSTRUCT.value):
@@ -32,23 +34,13 @@ class AlpacaPrompter:
 
     def match_prompt_style(self):
         if self.prompt_style == PromptStyle.INSTRUCT.value:
-            self.prompt_input = (
+            self.turn_format = "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
-                self.system_prompt
+            self.turn_no_input_format = (
-                + "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
+                "### Instruction:\n{instruction}\n\n### Response:\n"
             )
-            self.prompt_no_input = (
-                self.system_no_input_prompt
-                + "### Instruction:\n{instruction}\n\n### Response:\n"
-            )
-            self.response_split = "### Response:"
         if self.prompt_style == PromptStyle.CHAT.value:
-            self.prompt_input = (
+            self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
-                self.system_prompt + "USER: {instruction}\n{input}\nASSISTANT:"
+            self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
-            )
-            self.prompt_no_input = (
-                self.system_no_input_prompt + "USER: {instruction}\nASSISTANT:"
-            )
-            self.response_split = "ASSISTANT:"
 
     def build_prompt(
         self,
@@ -59,16 +51,17 @@ class AlpacaPrompter:
         # returns the full prompt from instruction and optional input
         # if a label (=response, =output) is provided, it's also appended.
         if input:
-            res = self.prompt_input.format(instruction=instruction, input=input)
+            res = self.system_prompt + self.turn_format.format(
+                instruction=instruction, input=input
+            )
         else:
-            res = self.prompt_no_input.format(instruction=instruction)
+            res = self.system_no_input_prompt + self.turn_no_input_format.format(
+                instruction=instruction
+            )
         if output:
             res = f"{res}{output}"
         yield res
 
-    def get_response(self, output: str) -> str:
-        return output.split(self.response_split)[1].strip()
-
 
 class UnpromptedPrompter(AlpacaPrompter):
     """
@@ -93,7 +86,10 @@ class MultipleChoiceExplainPrompter(AlpacaPrompter):
     """
 
     system_prompt = (
-        "Choose the answer that best answers the question. Explain your reasoning."
+        "Choose the answer that best answers the question. Explain your reasoning.\n"
+    )
+    system_no_input_prompt = (
+        "Choose the answer that best answers the question. Explain your reasoning.\n"
     )
 
 
@@ -102,7 +98,12 @@ class MultipleChoiceConcisePrompter(AlpacaPrompter):
     Prompter for multiple choice concise
     """
 
-    prompt_input = "Choose the answer that best answers the question. Be concise in your response.\n\nUSER: {instruction}\n{input}\nASSISTANT:\n"
+    system_prompt = "Choose the answer that best answers the question. Be concise in your response.\n\n"
+    system_no_input_prompt = "Choose the answer that best answers the question. Be concise in your response.\n\n"
+
+    def match_prompt_style(self):
+        self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
+        self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
 
 
 class SummarizeTLDRPrompter(AlpacaPrompter):
@@ -110,9 +111,12 @@ class SummarizeTLDRPrompter(AlpacaPrompter):
     Prompter for summarize TLDR
     """
 
-    prompt_no_input = (
+    system_prompt = ""
-        "USER: Summarize the following article as a TL;DR.\n{instruction}\nASSISTANT:"
+    system_no_input_prompt = ""
-    )
+
+    def match_prompt_style(self):
+        self.turn_format = "USER: Summarize the following article as a TL;DR.\n{instruction}\n{input}\nASSISTANT:"
+        self.turn_no_input_format = "USER: Summarize the following article as a TL;DR.\n{instruction}\nASSISTANT:"
 
 
 class CompletionPrompter:
@@ -128,9 +132,6 @@ class CompletionPrompter:
     ) -> Generator[str, None, None]:
         yield instruction
 
-    def get_response(self, output: str) -> str:
-        return output.strip()
-
 
 class GPTeacherPrompter(AlpacaPrompter):
     """
@@ -210,9 +211,6 @@ class ReflectAlpacaPrompter:
             res = f"{res}{label}"
         yield res
 
-    def get_response(self, output: str) -> str:
-        return output.split(self.response_split)[1].strip()
-
 
 class SeparatorStyle(Enum):
     """Different separator style."""
@@ -289,12 +287,6 @@ class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
             sep2=" ",
         )
 
-    # def match_prompt_style(self):
-    #     if self.prompt_style == PromptStyle.chat.value:
-    #         self.prompt_input = self.system_prompt + "USER: {instruction}\n{input}\nASSISTANT:"
-    #         self.prompt_no_input = self.system_no_input_prompt + "USER: {instruction}\nASSISTANT:"
-    #         self.response_split = "ASSISTANT:"
-
     def build_prompt(self, source) -> Generator[str, None, None]:
         # ignore the system prompt if provided
         if source[0]["from"] == "system":

src/axolotl/utils/data.py

@@ -37,7 +37,7 @@ from axolotl.prompters import (
 
 
 def load_tokenized_prepared_datasets(
-    tokenizer, cfg, default_dataset_prepared_path
+    split, tokenizer, cfg, default_dataset_prepared_path
 ) -> DatasetDict:
     tokenizer_name = tokenizer.__class__.__name__
     ds_hash = str(
@@ -49,6 +49,8 @@ def load_tokenized_prepared_datasets(
                     sorted([f"{d.path}:{d.type}:{d.shards}" for d in cfg.datasets])
                 )
                 + "|"
+                + split
+                + "|"
                 + tokenizer_name
             ).encode("utf-8")
         ).hexdigest()
@@ -66,7 +68,7 @@ def load_tokenized_prepared_datasets(
                 f"{cfg.push_dataset_to_hub}/{ds_hash}",
                 use_auth_token=use_auth_token,
             )
-            dataset = dataset["train"]
+            dataset = dataset[split]
     except Exception:  # pylint: disable=broad-except # nosec
         pass
 
@@ -134,8 +136,8 @@ def load_tokenized_prepared_datasets(
                 raise ValueError("unhandled dataset load")
             # support for using a subset of the data
             if d.shards:
-                if "train" in ds:
+                if split in ds:
-                    ds = ds.shuffle(seed=seed)["train"].shard(
+                    ds = ds.shuffle(seed=seed)[split].shard(
                         num_shards=d.shards, index=0
                     )
                 else:
@@ -144,8 +146,8 @@ def load_tokenized_prepared_datasets(
             d_type_split = d_type.split(":")
             d_base_type = d_type_split[0]
             d_prompt_style = d_type_split[1] if len(d_type_split) > 1 else None
-            if "train" in ds:
+            if split in ds:
-                ds = ds["train"]
+                ds = ds[split]
             if ds_strategy := load(d.type, tokenizer, cfg):
                 ds_wrapper = TokenizedPromptDataset(ds_strategy, ds)
                 datasets.append(ds_wrapper)
@@ -319,7 +321,6 @@ def load_prepare_datasets(
                     f"{cfg.push_dataset_to_hub}/{ds_hash}",
                     use_auth_token=use_auth_token,
                 )
-                dataset = dataset["train"]
         except Exception:  # pylint: disable=broad-except # nosec
             pass
 
@@ -339,28 +340,37 @@ def load_prepare_datasets(
                     f"{cfg.push_dataset_to_hub}/{ds_hash}", private=True
                 )
         else:
-            dataset = load_tokenized_prepared_datasets(
+            dataset_train = load_tokenized_prepared_datasets(
-                tokenizer, cfg, default_dataset_prepared_path
+                "train", tokenizer, cfg, default_dataset_prepared_path
             )
-
+            dataset_test = load_tokenized_prepared_datasets(
+                "test", tokenizer, cfg, default_dataset_prepared_path
+            )
+            dataset = DatasetDict({"train": dataset_train, "test": dataset_test})
             if cfg.seed:
                 dataset = dataset.shuffle(seed=cfg.seed)
 
-            constant_len_dataset = ConstantLengthDataset(
+            constant_len_dataset_train = ConstantLengthDataset(
                 tokenizer,
-                [dataset],
+                [dataset["train"]],
+                seq_length=max_packed_sequence_len,
+            )
+            constant_len_dataset_test = ConstantLengthDataset(
+                tokenizer,
+                [dataset["test"]],
                 seq_length=max_packed_sequence_len,
             )
             logging.info(
                 f"packing master dataset to len: {cfg.max_packed_sequence_len}"
             )
-            dataset = Dataset.from_list(list(constant_len_dataset))
+            dataset_train = Dataset.from_list(list(constant_len_dataset_train))
+            dataset_test = Dataset.from_list(list(constant_len_dataset_test))
 
             # filter out bad data
-            dataset = Dataset.from_list(
+            dataset_train = Dataset.from_list(
                 [
                     d
-                    for d in dataset
+                    for d in dataset_train
                     if len(d["input_ids"]) < cfg.sequence_len
                     and len(d["input_ids"]) > 0
                     and len(d["input_ids"]) == len(d["attention_mask"])
@@ -368,6 +378,19 @@ def load_prepare_datasets(
                 ]
             )
 
+            # filter out bad data
+            dataset_test = Dataset.from_list(
+                [
+                    d
+                    for d in dataset_test
+                    if len(d["input_ids"]) < cfg.sequence_len
+                    and len(d["input_ids"]) > 0
+                    and len(d["input_ids"]) == len(d["attention_mask"])
+                    and len(d["input_ids"]) == len(d["labels"])
+                ]
+            )
+            dataset = DatasetDict({"train": dataset_train, "test": dataset_test})
+
             if cfg.local_rank == 0:
                 logging.info(
                     f"Saving packed prepared dataset to disk... {prepared_ds_path}"
@@ -382,9 +405,14 @@ def load_prepare_datasets(
                         private=True,
                     )
     else:
+        # dataset_train = load_tokenized_prepared_datasets(
         dataset = load_tokenized_prepared_datasets(
-            tokenizer, cfg, default_dataset_prepared_path
+            "train", tokenizer, cfg, default_dataset_prepared_path
         )
+        # dataset_test = load_tokenized_prepared_datasets(
+        #     "test", tokenizer, cfg, default_dataset_prepared_path
+        # )
+        # dataset = DatasetDict({"train": dataset_train, "test": dataset_test})
 
     if cfg.dataset_shard_num and cfg.dataset_shard_idx is not None:
         logging.info(
@@ -399,6 +427,9 @@ def load_prepare_datasets(
         dataset = dataset.train_test_split(test_size=cfg.val_set_size, shuffle=False)
         train_dataset = dataset["train"]
         eval_dataset = dataset["test"]
+    elif "train" in dataset:
+        train_dataset = dataset["train"]
+        eval_dataset = dataset["test"]
     else:
         train_dataset = dataset
         eval_dataset = None

src/axolotl/utils/models.py

@@ -34,15 +34,20 @@ def load_tokenizer(
     tokenizer_type,
     cfg,
 ):
+    use_fast = True  # this is the default
+    if cfg.tokenizer_use_fast is not None:
+        use_fast = cfg.tokenizer_use_fast
     if tokenizer_type:
         tokenizer = getattr(transformers, tokenizer_type).from_pretrained(
             tokenizer_config,
             trust_remote_code=cfg.trust_remote_code or False,
+            use_fast=use_fast,
         )
     else:
         tokenizer = AutoTokenizer.from_pretrained(
             tokenizer_config,
             trust_remote_code=cfg.trust_remote_code or False,
+            use_fast=use_fast,
         )
 
     logging.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")

src/axolotl/utils/tokenization.py

@@ -34,3 +34,5 @@ def check_example_labels(example, tokenizer):
 
     logging.info(" ".join(colored_tokens))
     logging.info("\n\n\n")
+
+    return " ".join(colored_tokens)

src/axolotl/utils/trainer.py

@@ -124,6 +124,10 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
     if cfg.max_grad_norm:
         training_arguments_kwargs["max_grad_norm"] = cfg.max_grad_norm
 
+    if cfg.push_to_hub_model_id:
+        training_arguments_kwargs["push_to_hub_model_id"] = cfg.push_to_hub_model_id
+        training_arguments_kwargs["push_to_hub"] = True
+
     training_args = transformers.TrainingArguments(
         per_device_train_batch_size=cfg.micro_batch_size,
         per_device_eval_batch_size=cfg.eval_batch_size
@@ -133,9 +137,9 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
         eval_accumulation_steps=cfg.gradient_accumulation_steps,
         num_train_epochs=cfg.num_epochs,
         learning_rate=cfg.learning_rate,
-        evaluation_strategy="steps" if cfg.val_set_size > 0 else "no",
+        evaluation_strategy="steps",
         save_strategy="steps" if cfg.save_steps else "epoch",
-        eval_steps=cfg.eval_steps if cfg.val_set_size > 0 else None,
+        eval_steps=cfg.eval_steps,
         save_steps=cfg.save_steps,
         output_dir=cfg.output_dir,
         save_total_limit=3,

tests/test_prompt_tokenizers.py

@@ -7,11 +7,15 @@ from pathlib import Path
 from transformers import AutoTokenizer
 
 from axolotl.prompt_strategies.alpaca_chat import NoSystemPrompter
+from axolotl.prompt_strategies.alpaca_w_system import (
+    InstructionWSystemPromptTokenizingStrategy,
+    SystemDataPrompter,
+)
 from axolotl.prompt_tokenizers import (
     AlpacaPromptTokenizingStrategy,
     ShareGPTPromptTokenizingStrategy,
 )
-from axolotl.prompters import AlpacaPrompter, ShareGPTPrompter
+from axolotl.prompters import AlpacaPrompter, PromptStyle, ShareGPTPrompter
 
 logging.basicConfig(level="INFO")
 
@@ -96,5 +100,39 @@ class TestPromptTokenizationStrategies(unittest.TestCase):
         assert example["labels"][world_idx - 1] == -100
 
 
+class InstructionWSystemPromptTokenizingStrategyTest(unittest.TestCase):
+    """
+    Test class for prompt tokenization strategies with sys prompt from the dataset
+    """
+
+    def setUp(self) -> None:
+        # pylint: disable=duplicate-code
+        self.tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-7b")
+        self.tokenizer.add_special_tokens(
+            {
+                "bos_token": "<s>",
+                "eos_token": "</s>",
+                "unk_token": "<unk>",
+            }
+        )
+
+    def test_system_alpaca(self):
+        prompter = SystemDataPrompter(PromptStyle.CHAT.value)
+        strat = InstructionWSystemPromptTokenizingStrategy(
+            prompter,
+            self.tokenizer,
+            False,
+            2048,
+        )
+        sample = {
+            "system": "use cot",
+            "instruction": "hello!",
+            "output": "Hi! How can I help?",
+        }
+        example = strat.tokenize_prompt(sample)
+        assert example["input_ids"][0:3] == [1, 671, 20118]  # <s>use cot
+        assert example["input_ids"][3] == 11889  # USER
+
+
 if __name__ == "__main__":
     unittest.main()

tests/test_prompters.py

@@ -2,7 +2,13 @@
 
 import unittest
 
-from axolotl.prompters import AlpacaPrompter, PromptStyle
+from axolotl.prompt_strategies.alpaca_w_system import SystemDataPrompter
+from axolotl.prompters import (
+    AlpacaPrompter,
+    MultipleChoiceExplainPrompter,
+    PromptStyle,
+    UnpromptedPrompter,
+)
 
 
 class AlpacaPrompterTest(unittest.TestCase):
@@ -55,3 +61,64 @@ class AlpacaPrompterTest(unittest.TestCase):
         assert "### Response:" not in res
         assert "USER:" in res
         assert "ASSISTANT:" in res
+
+    def test_system_prompt(self):
+        prompter = SystemDataPrompter(prompt_style=PromptStyle.CHAT.value)
+        res = next(
+            prompter.build_prompt_w_system(
+                "use cot", "tell me a joke about the following", "alpacas"
+            )
+        )
+        assert "use cot" in res
+        assert res.startswith("use cot")
+        assert "### Instruction:" not in res
+        assert "### Input:" not in res
+        assert "alpacas" in res
+        assert "### Response:" not in res
+        assert "USER:" in res
+        assert "ASSISTANT:" in res
+
+
+class UnpromptedPrompterTest(unittest.TestCase):
+    """
+    Test class for UnpromptedPrompter with no system prompts
+    """
+
+    def test_prompt_style_w_none(self):
+        prompter = UnpromptedPrompter(prompt_style=None)
+        res = next(prompter.build_prompt("tell me a joke"))
+        assert "### Instruction:" in res
+        assert "tell me a joke" in res
+        assert res.startswith("###")
+
+    def test_prompt_style_w_instruct(self):
+        prompter = UnpromptedPrompter(prompt_style=PromptStyle.INSTRUCT.value)
+        res = next(
+            prompter.build_prompt("tell me a joke about the following", "alpacas")
+        )
+        assert "### Instruction:" in res
+        assert "tell me a joke" in res
+        assert res.startswith("###")
+
+    def test_prompt_style_w_chat(self):
+        prompter = UnpromptedPrompter(prompt_style=PromptStyle.CHAT.value)
+        res = next(
+            prompter.build_prompt("tell me a joke about the following", "alpacas")
+        )
+        assert "USER:" in res
+        assert "tell me a joke" in res
+        assert res.startswith("USER:")
+
+
+class MultipleChoiceExplainPrompterTest(unittest.TestCase):
+    """
+    Test class for MultipleChoiceExplainPrompter
+    """
+
+    def test_prompt_style_w_chat(self):
+        prompter = MultipleChoiceExplainPrompter(prompt_style=PromptStyle.CHAT.value)
+        res = next(prompter.build_prompt("choose one", "- A\n- B\n- C", "C"))
+        assert "USER:" in res
+        assert "choose one" in res
+        assert "Choose the answer that best answers the question." in res
+        assert "- A\n- B\n- C" in res

tests/test_tokenizers.py

@@ -0,0 +1,31 @@
+"""
+Test cases for the tokenizer loading
+"""
+import unittest
+
+from axolotl.utils.dict import DictDefault
+from axolotl.utils.models import load_tokenizer
+
+
+class TestTokenizers(unittest.TestCase):
+    """
+    test class for the load_tokenizer fn
+    """
+
+    def test_default_use_fast(self):
+        cfg = DictDefault({})
+        tokenizer = load_tokenizer("huggyllama/llama-7b", None, cfg)
+        assert "Fast" in tokenizer.__class__.__name__
+
+    def test_dont_use_fast(self):
+        cfg = DictDefault(
+            {
+                "tokenizer_use_fast": False,
+            }
+        )
+        tokenizer = load_tokenizer("huggyllama/llama-7b", None, cfg)
+        assert "Fast" not in tokenizer.__class__.__name__
+
+
+if __name__ == "__main__":
+    unittest.main()