Initial upload of fine‑tuned Gemma + custom tokenizer

gemma_explicit_tokenizer.py

@@ -0,0 +1,374 @@
+"""
+Custom Gemma Tokenizer for explicit Format
+
+This tokenizer implements the explicit format for message processing:
+Format: Uses the standard chat template with proper role labels (user/assistant)
+
+The explicit format uses the model's built-in chat template and includes proper 
+loss computation flags for training.
+
+To save:
+uv run tokenizers/gemma_explicit_tokenizer.py 
+which will save the tokenizer to the repos/explicit-gemma-tokenizer directory.
+mkdir repos/explicit12b
+# copy model over
+cp models_v8/base_modified-google-gemma-3-12b-pt-/models/_explicit/checkpoint-8/* repos/explicit12b/
+# copy tokenizer over
+cp repos/explicit-gemma-tokenizer/* repos/explicit12b/
+# upload to hf
+
+uv run upload_to_hf.py \
+  --folder repos/explicit12b \
+  --repo-id tsor13/explicit12b
+"""
+
+from typing import List, Dict, Any, Optional, Union
+from transformers import AutoTokenizer
+from transformers.models.gemma.tokenization_gemma_fast import GemmaTokenizerFast
+from transformers.models.gemma.tokenization_gemma import GemmaTokenizer
+import warnings
+import difflib
+import json
+import os
+import sys
+
+# Add parent directory to path to import chat_utils
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from chat_utils import chat_messages_to_text_loss, chat_messages_to_raw_text
+
+
+class GemmaExplicitTokenizer(GemmaTokenizerFast):
+    """
+    Custom tokenizer for Gemma models that implements explicit format message processing.
+    
+    This tokenizer formats messages using the explicit format where:
+    - Messages use the standard chat template with proper role labels
+    - Uses the model's built-in chat formatting
+    - Loss is computed on the assistant/output sections
+    
+    Attributes:
+        start_string (str): The starting string used for output generation (depends on tokenizer)
+        end_string (str): The ending string used for output generation (depends on tokenizer)
+    """
+    
+    def __init__(self, *args, **kwargs):
+        """
+        Initialize the custom tokenizer.
+        
+        Accepts the same arguments as GemmaTokenizerFast.
+        """
+        super().__init__(*args, **kwargs)
+        
+        # For explicit format, we use the tokenizer's own chat template
+        # The start/end strings will be determined by the chat template
+        self.start_string = None  # Will be set dynamically
+        self.end_string = None    # Will be set dynamically
+        
+        # Add custom attributes to the tokenizer config for saving/loading
+        if not hasattr(self, 'init_kwargs'):
+            self.init_kwargs = {}
+        self.init_kwargs['start_string'] = self.start_string
+        self.init_kwargs['end_string'] = self.end_string
+    
+    @classmethod
+    def from_gemma_pretrained(cls, pretrained_model_name_or_path, *args, **kwargs):
+        """
+        Load a tokenizer from a pretrained model or path.
+        
+        This method ensures our custom class is used instead of the base GemmaTokenizerFast.
+        """
+        # Load the base tokenizer first to get all configuration
+        base_tokenizer = GemmaTokenizerFast.from_pretrained(
+            pretrained_model_name_or_path, *args, **kwargs
+        )
+        
+        # Create new instance of our custom class by copying the base tokenizer
+        custom_tokenizer = cls.__new__(cls)
+        
+        # Copy all attributes from base tokenizer
+        for attr, value in base_tokenizer.__dict__.items():
+            setattr(custom_tokenizer, attr, value)
+        
+        # Initialize our custom attributes for explicit format
+        custom_tokenizer.start_string = None  # Will be determined dynamically
+        custom_tokenizer.end_string = None    # Will be determined dynamically
+        
+        # Update init_kwargs to include our custom attributes
+        if not hasattr(custom_tokenizer, 'init_kwargs'):
+            custom_tokenizer.init_kwargs = {}
+        custom_tokenizer.init_kwargs['start_string'] = custom_tokenizer.start_string
+        custom_tokenizer.init_kwargs['end_string'] = custom_tokenizer.end_string
+        
+        return custom_tokenizer
+    
+    def save_pretrained(self, save_directory: Union[str, os.PathLike], **kwargs):
+        """
+        Save the tokenizer to a directory, including custom configuration.
+        """
+        # Call parent save method
+        super().save_pretrained(save_directory, **kwargs)
+        
+        # Save custom configuration
+        config_file = os.path.join(save_directory, "tokenizer_config.json")
+        if os.path.exists(config_file):
+            with open(config_file, 'r') as f:
+                config = json.load(f)
+        else:
+            config = {}
+        
+        # Add our custom class info
+        config["tokenizer_class"] = "GemmaExplicitTokenizer"
+        config["start_string"] = self.start_string
+        config["end_string"] = self.end_string
+        # Point to our custom class in the uploaded file
+        config["auto_map"] = {
+            "AutoTokenizer": ["gemma_explicit_tokenizer.GemmaExplicitTokenizer", "gemma_explicit_tokenizer.GemmaExplicitTokenizer"]
+        }
+        
+        with open(config_file, 'w') as f:
+            json.dump(config, f, indent=2)
+    
+    def messages_to_loss_texts(
+            self,
+            messages: List[Dict[str, Any]], 
+            loss_on_start_token: bool = False, 
+        ) -> List[Dict[str, Any]]:
+        """
+        From messages (description / input / output) to texts (text / compute_loss) with whether or not loss should be calculated on the text for training.
+        Uses the explicit format from chat_utils.
+        """
+        return chat_messages_to_text_loss(messages, self, loss_on_start_token, start_gen_as="output")
+    
+    def messages_to_text(
+            self, 
+            messages: List[Dict[str, Any]], 
+            start_generation: bool = False, 
+        ) -> str:
+        """
+        Messages (description / input / output) to raw text (text).
+        Uses the explicit format from chat_utils.
+        """
+        return chat_messages_to_raw_text(messages, self, start_generation=start_generation, start_gen_as="output")
+    
+
+    def tokenize_messages(
+            self, 
+            messages: List[Dict[str, Any]] | List[List[Dict[str, Any]]],
+            start_generation: bool = False, 
+            **kwargs,
+        ):
+        """
+        For tokenizing from messages to texts. Supports batching. Good for generation
+        """
+        if isinstance(messages, list) and isinstance(messages[0], list):
+            # Handle list of lists of messages
+            all_texts = []
+            for message_list in messages:
+                texts = self.messages_to_text(message_list, start_generation)
+                all_texts.append(texts)
+        else:
+            # Handle single list of messages
+            texts = self.messages_to_text(messages, start_generation)
+            all_texts = [texts]
+        
+        # Tokenize all texts
+        processed = self(text=all_texts, **kwargs)
+        return processed
+    
+    
+    def tokenize_loss_texts(
+            self, 
+            texts: List[Dict[str, Any]], 
+            loss_on_start_token: bool = False, 
+            loss_on_eos: bool = False, 
+            include_eos: bool = True,
+        ):
+        """
+        Tokenize texts (text / compute_loss) to tokenized texts (input_ids / attention_mask / labels).
+
+        Needs more complex logic to handle the back and forth labeling.
+        """
+        if loss_on_eos:
+            raise ValueError("Loss on EOS is not currently supported.")
+        
+        # Handle single string input
+        if isinstance(texts, str):
+            processed = self(text=texts)
+            # Add EOS token if needed
+            if (self.eos_token_id is not None and 
+                processed["input_ids"][-1] != self.eos_token_id):
+                processed["input_ids"] = processed["input_ids"] + [self.eos_token_id]
+                processed["attention_mask"] = processed["attention_mask"] + [1]
+            return processed
+        
+        # Handle list of text dictionaries
+        all_processed = []
+        all_texts = ''
+        example_inds = []
+        dataset_inds = []
+        
+        for i, item in enumerate(texts):
+            processed = self(text=item["text"])
+            
+            # Remove BOS token from all but first item
+            if i != 0 and self.bos_token_id == processed["input_ids"][0]:
+                processed["input_ids"] = processed["input_ids"][1:]
+                processed["attention_mask"] = processed["attention_mask"][1:]
+            
+            # Remove EOS token if present at the end
+            if processed["input_ids"][-1] == self.eos_token_id:
+                processed["input_ids"] = processed["input_ids"][:-1]
+                processed["attention_mask"] = processed["attention_mask"][:-1]
+            
+            # Check for EOS token in the middle (with special handling for <|im_end|>)
+            if self.eos_token_id in processed["input_ids"]:
+                if not self.decode([self.eos_token_id]) == "<|im_end|>":
+                    raise ValueError(f"EOS token is present in input_ids: {processed['input_ids']}. Not currently supported.")
+            
+            # Set labels based on compute_loss flag
+            if item["compute_loss"]:
+                processed["labels"] = processed["input_ids"].copy()
+            else:
+                processed["labels"] = [-100] * len(processed["input_ids"])
+            
+            # Remove duplicate BOS tokens
+            if all_processed:
+                if processed["input_ids"][0] == self.bos_token_id:
+                    processed["input_ids"] = processed["input_ids"][1:]
+                    processed["attention_mask"] = processed["attention_mask"][1:]
+                    processed["labels"] = processed["labels"][1:]
+            
+            all_processed.append(processed)
+            all_texts += item["text"]
+            
+            # Handle example indices
+            this_num = -1
+            if 'example_ind' in item.keys():
+                if item["example_ind"] is not None:
+                    this_num = item["example_ind"]
+            example_inds.extend([this_num] * len(processed["input_ids"]))
+            
+            # Handle dataset indices
+            dataset_ind = -1
+            if "data_id" in item.keys():
+                if item["data_id"] is not None:
+                    dataset_ind = item["data_id"]
+            dataset_inds.extend([dataset_ind] * len(processed["input_ids"]))
+        
+        # Combine all processed results
+        processed = all_processed[0].copy()
+        processed["input_ids"] = [item for sublist in [p["input_ids"] for p in all_processed] for item in sublist]
+        processed["attention_mask"] = [item for sublist in [p["attention_mask"] for p in all_processed] for item in sublist]
+        processed["labels"] = [item for sublist in [p["labels"] for p in all_processed] for item in sublist]
+        processed["example_inds"] = example_inds
+        processed["data_ids"] = dataset_inds
+        
+        # Validate by tokenizing all_texts at once and comparing
+        processed_all = self(text=all_texts)
+        if len(processed_all["input_ids"]) != len(processed["input_ids"]):
+            warnings.warn(f"All texts are not the same length as the first text. Please check your dataset. {len(processed_all['input_ids'])} != {len(processed['input_ids'])}")
+            
+            # Generate diff for debugging
+            all_text = self.decode(processed_all["input_ids"], skip_special_tokens=False)
+            processed_text = self.decode(processed["input_ids"], skip_special_tokens=False)
+            
+            diff = difflib.unified_diff(all_text.splitlines(), processed_text.splitlines())
+            diff_str = "\n".join(diff)
+            print("Diff between texts:")
+            print(diff_str)
+            
+            # Token diff
+            all_tokens_str = '\n'.join([str(s) for s in processed_all["input_ids"]])
+            processed_tokens_str = '\n'.join([str(s) for s in processed["input_ids"]])
+            token_diff = difflib.unified_diff(all_tokens_str.splitlines(), processed_tokens_str.splitlines())
+            token_diff_str = "\n".join(token_diff)
+            print("Diff between tokenized texts:")
+            print(token_diff_str)
+        
+        # Add EOS token if needed
+        if (self.eos_token_id is not None and 
+            processed["input_ids"][-1] != self.eos_token_id):
+            processed["input_ids"] = processed["input_ids"] + [self.eos_token_id]
+            processed["example_inds"] = processed["example_inds"] + [-1]
+            processed["attention_mask"] = processed["attention_mask"] + [1]
+            if processed["labels"] is not None:
+                if loss_on_eos:
+                    processed["labels"] = processed["labels"] + [self.eos_token_id]
+                else:
+                    processed["labels"] = processed["labels"] + [-100]
+            if "data_ids" in processed:
+                processed["data_ids"] = processed["data_ids"] + [-1]
+            
+        if not include_eos:
+            # check if EOS token is present
+            if processed["input_ids"][-1] == self.eos_token_id:
+                # remove EOS token
+                processed["input_ids"] = processed["input_ids"][:-1]
+                processed["attention_mask"] = processed["attention_mask"][:-1]
+                processed["labels"] = processed["labels"][:-1]
+                processed["example_inds"] = processed["example_inds"][:-1]
+                processed["data_ids"] = processed["data_ids"][:-1]
+        
+        return processed
+    
+    def tokenize_messages(
+            self, 
+            messages: List[Dict[str, Any]], 
+            loss_on_start_token: bool = False, 
+            loss_on_eos: bool = False,
+            include_eos: bool = True,
+        ) -> Dict[str, Any]:
+        """
+        Intended for tokenize from messages to tokenized texts with the loss applied.
+        """
+        # First convert messages to text with loss computation flags
+        texts = self.messages_to_loss_texts(messages, loss_on_start_token)
+        
+        # Then tokenize the texts
+        return self.tokenize_loss_texts(texts, loss_on_eos, include_eos = include_eos)
+    
+
+
+
+# Register tokenizer classes for AutoTokenizer
+AutoTokenizer.register("GemmaExplicitTokenizer", slow_tokenizer_class=None, fast_tokenizer_class=GemmaExplicitTokenizer)
+
+
+if __name__ == "__main__":
+    # Example usage
+    # for first load
+    custom_tokenizer = GemmaExplicitTokenizer.from_gemma_pretrained("google/gemma-3-1b-it")
+
+    # for subsequent loads
+    # custom_tokenizer = GemmaExplicitTokenizer.from_pretrained("tsor13/explicit-gemma-12b-pt")
+    # custom_tokenizer = GemmaExplicitTokenizer.from_pretrained("repos/explicit-gemma-12b-pt")
+    
+    # Test messages in role/content format
+    messages = [
+        {"role": "description", "content": "This is a test task"},
+        {"role": "input", "content": "What is 2+2?"},
+        {"role": "output", "content": "4"},
+        {"role": "input", "content": "What is 3+3?"},
+        # {"role": "output", "content": "6"}
+    ]
+
+    # get messages to text_loss
+    texts = custom_tokenizer.messages_to_loss_texts(messages)
+    print("Texts with loss flags:")
+    for i, text in enumerate(texts):
+        print(f"  {i}: {text}")
+
+    text = custom_tokenizer.messages_to_text(messages, start_generation=True)
+    print(f"\nFull text with generation prompt:")
+    print(text)
+    
+    print("\nTesting save/load cycle:")
+    # Test saving and loading
+    tokenizer_path = "repos/explicit-gemma-tokenizer"
+    custom_tokenizer.save_pretrained(tokenizer_path)
+    print("Tokenizer saved successfully!")
+
+    # also save this file in the tokenizer_path
+    import shutil
+    shutil.copy(__file__, os.path.join(tokenizer_path, "gemma_explicit_tokenizer.py"))
+    print("GemmaExplicitTokenizer.py saved successfully!")

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482be2455e637e399de5e4c8afaec5d2675ec11f89137e526362b82b23cedb4b
+oid sha256:542b2874d19bff3762d350e9c1bd370e50d80c5f709b80f1c7a443fc01849b20
 size 4979902192

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f80968dd4e284d30ed74416856e65c7344cb8ed822d3f833e711249692160e
+oid sha256:b4ffcce1c51995b5dc648d237497030a2f779a4cd33761be3737393254886079
 size 4931296592

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb6398002e8b6604cef8459094542dcccbfd027bacd105d4a9c82f95ea16192
+oid sha256:092ae6527089321ed068b3103a101b768b3953bd4c43140bd82bdc423d0795cb
 size 4931296656

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9e1e56ed4e0108727c4c549ee28ec2af3da9f48369c8fad1527a2978d19e20
+oid sha256:422970ba53b0cb3fc42ddd8dc27077b25ee953c4d64df6861b35ee92a4529d6d
 size 4931296656

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f435f220bcf30ac3f7e864f113cdf55f1c2d86b35674047ab703a957ec75a5
+oid sha256:71868eb31768e9d0d97fe9207f4abb09a9332e565552cfc762a5b9d0dd1b905f
 size 4601000928

tokenizer_config.json

@@ -51325,8 +51325,9 @@
   },
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
   "clean_up_tokenization_spaces": false,
-  "end_string": "<end_of_turn>",
+  "end_string": null,
   "eoi_token": "<end_of_image>",
   "eos_token": "<eos>",
   "extra_special_tokens": {
@@ -51337,16 +51338,17 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
-  "start_string": "<start_of_turn>",
-  "tokenizer_class": "GemmaSpecialTokenizer",
+  "start_string": null,
+  "tokenizer_class": "GemmaExplicitTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false,
   "auto_map": {
     "AutoTokenizer": [
-      "gemma_special_tokenizer.GemmaSpecialTokenizer",
-      "gemma_special_tokenizer.GemmaSpecialTokenizer"
+      "gemma_explicit_tokenizer.GemmaExplicitTokenizer",
+      "gemma_explicit_tokenizer.GemmaExplicitTokenizer"
     ]
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e21928f1882517a4b05718e3914cb90eb7110650d66245962ef389df1995890
+oid sha256:e4b89185f26b9cbdf0d6a835b8d4fb2bf8c6584347553dcaa366582ca993a82c
 size 7377