Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1 @@
+{%- for message in messages -%}{%- if loop.first and messages[0]['role'] != 'system' -%}<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>{%- endif -%}{%- if message['role'] == 'system' -%}<|im_system|>{%- endif -%}{%- if message['role'] == 'user' -%}<|im_user|>{%- endif -%}{%- if message['role'] == 'assistant' -%}<|im_assistant|>{%- endif -%}{{ message['role'] }}<|im_middle|>{{message['content']}}<|im_end|>{%- endfor -%}{%- if add_generation_prompt -%}<|im_assistant|>assistant<|im_middle|>{%- endif -%}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 163584,
+  "eos_token_id": 163585,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "kv_lora_rank": 128,
+  "max_position_embeddings": 1024,
+  "model_type": "kimi_k2",
+  "moe_intermediate_size": 512,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 8,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "num_nextn_predict_layers": 0,
+  "pretraining_tp": 1,
+  "q_lora_rank": 384,
+  "qk_nope_head_dim": 32,
+  "qk_rope_head_dim": 32,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "v_head_dim": 64,
+  "vocab_size": 163840
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d053a8cc99a48964244dd3eef30c4f7fcfbe998f3b4cd1dc03f94dde709c1cd
+size 831641000

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|im_system|>",
+    "<|im_middle|>"
+  ],
+  "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
+  }
+}

tiktoken.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103
+size 2795286

tokenization_moonshot.py

@@ -0,0 +1,301 @@
+import os
+import tiktoken
+
+from logging import getLogger
+from pathlib import Path
+from typing import (
+    cast,
+    Tuple,
+    Dict,
+    Iterator,
+    List,
+    Union,
+    Optional,
+)
+from shutil import copyfile
+import numpy as np
+from tiktoken.load import load_tiktoken_bpe
+from tokenizers import AddedToken
+from transformers import  PreTrainedTokenizerFast
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
+
+
+
+logger = getLogger(__name__)
+VOCAB_FILES_NAMES = {"vocab_file": "tiktoken.model"}
+SPIECE_UNDERLINE = "▁"
+
+class TikTokenTokenizer(PreTrainedTokenizer):
+    """
+    Tokenizing and encoding/decoding text using the Tiktoken tokenizer. See megatron/tokenizer/tiktoken_tokenizer.py.
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
+
+    Args:
+        vocab_file (`str`):
+            The path to the Tiktoken model file.
+        bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|begin_of_text|>",`):
+            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
+        eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|end_of_text|>"`):
+            The end of sequence token.
+        unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|reserved_special_token_249|>"`):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead. The second to last item in special_tokens. 
+        pad_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|reserved_special_token_250|>"`):
+            The token used for padding, for example when batching sequences of different lengths.
+        additional_special_tokens (list of `str`, *optional*):
+            A tuple or a list of additional tokens, which will be marked as `special`, meaning that they will be
+            skipped when decoding if `skip_special_tokens` is set to `True`.
+    """
+    
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    model_input_names = ["input_ids", "attention_mask"]
+
+    special_tokens: Dict[str, int]
+
+    num_reserved_special_tokens = 256
+
+    pat_str = "|".join(
+        [
+            r"""[\p{Han}]+""",
+            r"""[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?""",
+            r"""[^\r\n\p{L}\p{N}]?[\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]+[\p{Ll}\p{Lm}\p{Lo}\p{M}&&[^\p{Han}]]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?""",
+            r"""\p{N}{1,3}""",
+            r""" ?[^\s\p{L}\p{N}]+[\r\n]*""",
+            r"""\s*[\r\n]+""",
+            r"""\s+(?!\S)""",
+            r"""\s+""",
+        ]
+    )
+
+    def __init__(
+        self,
+        vocab_file,
+        bos_token: Union[str, AddedToken]="[BOS]",
+        eos_token: Union[str, AddedToken]="[EOS]",
+        unk_token: Union[str, AddedToken]="[UNK]",
+        pad_token: Union[str, AddedToken]="[PAD]",
+        additional_special_tokens: Optional[List[str]] = None,
+        added_tokens_decoder: Optional[dict] = None,
+        **kwargs,
+    ):
+        assert os.path.isfile(vocab_file), vocab_file
+        if additional_special_tokens is None:
+            additional_special_tokens = [
+                "<|im_end|>",
+                "<|im_middle|>",
+                "<|im_user|>",
+                "<|im_assistant|>",
+                "<|im_system|>"
+            ]
+        special_tokens_mapping = {i: added_tokens_decoder[i].content for i in added_tokens_decoder}
+
+        special_tokens = [str(bos_token), str(eos_token)] + additional_special_tokens + [str(unk_token), str(pad_token)] 
+
+        self.vocab_file = vocab_file
+        mergeable_ranks = load_tiktoken_bpe(vocab_file)
+        num_base_tokens = len(mergeable_ranks)
+        self.special_tokens = {
+            special_tokens_mapping.get(i, f"<|reserved_token_{i}|>"): i \
+                for i in range(num_base_tokens, num_base_tokens + self.num_reserved_special_tokens + 2)
+        }
+
+        self.model = tiktoken.Encoding(
+            name=Path(vocab_file).name,
+            pat_str=self.pat_str,
+            mergeable_ranks=mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        logger.info(f"Reloaded tiktoken model from {vocab_file}")
+
+        self.n_words: int = self.model.n_vocab
+        # BOS / EOS token IDs
+        self.bos_id: int = self.special_tokens[str(bos_token)]
+        self.eos_id: int = self.special_tokens[str(eos_token)]
+        logger.info(
+            f"#words: {self.n_words} - BOS ID: {self.bos_id} - EOS ID: {self.eos_id}"
+        )
+
+        self.pad_id: int = self.special_tokens[str(pad_token)]
+        self.unk_id: int = self.special_tokens[str(unk_token)]
+
+        self.byte_encoder = bytes_to_unicode()
+        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
+
+        self.decoder = {}
+        for i in range(self.n_words):
+            # Taken from https://gist.github.com/xenova/a452a6474428de0182b17605a98631ee
+            decoding = ''.join([
+                self.byte_encoder[ord(char)] for char in
+                self.model.decode_single_token_bytes(i).decode('latin-1')
+            ])
+            self.decoder[i] = decoding
+
+        self.encoder = {}
+        for i in range(self.n_words):
+            if i in self.decoder:
+                self.encoder[self.decoder[i]] = i
+
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            additional_special_tokens=additional_special_tokens,
+            **kwargs,
+        )
+        self.all_special_ids_set = set(self.all_special_ids)
+
+    def encode(
+        self,
+        text: str,
+        allow_special_tokens: bool = True,
+        **kwargs
+    ) -> List[int]:
+        """
+        Encodes a string into a list of token IDs.
+
+        Args:
+            text (str): The input string to be encoded.
+
+        Returns:
+            list[int]: A list of token IDs.
+        """
+        # If there are other args, we should call super().encode because there are a lot of code
+        # to handle those args. supper().encode finally will call _tokenize and _convert_token_to_id.
+        if len(kwargs) > 0:
+            return super().encode(text, **kwargs)
+
+        assert type(text) is str
+
+        # The tiktoken tokenizer can handle <=400k chars without
+        # pyo3_runtime.PanicException.
+        TIKTOKEN_MAX_ENCODE_CHARS = 400_000
+
+        # https://github.com/openai/tiktoken/issues/195
+        # Here we iterate over subsequences and split if we exceed the limit
+        # of max consecutive non-whitespace or whitespace characters.
+        MAX_NO_WHITESPACES_CHARS = 25_000
+
+        substrs = (
+            substr
+            for i in range(0, len(text), TIKTOKEN_MAX_ENCODE_CHARS)
+            for substr in self._split_whitespaces_or_nonwhitespaces(
+                text[i : i + TIKTOKEN_MAX_ENCODE_CHARS], MAX_NO_WHITESPACES_CHARS
+            )
+        )
+        t: List[int] = []
+        for substr in substrs:
+            if allow_special_tokens:
+                t.extend(
+                    # we should consider special token as a common token
+                    self.model.encode(
+                        substr,
+                        allowed_special="all",
+                    )
+                )
+            else:
+                t.extend(
+                    # we should consider special token as a common token
+                    self.model.encode(
+                        substr,
+                        disallowed_special=(),
+                    )
+                )
+        return t
+
+    def decode(
+        self,
+        token_ids: Union[int, List[int]],
+        **kwargs
+    ) -> str:
+        """
+        Decodes a list of token IDs into a string.
+
+        Args:
+            t (List[int]): The list of token IDs to be decoded.
+
+        Returns:
+            str: The decoded string.
+        """
+        # If there are other args, we should call super().decode because there are a lot of code
+        # to handle those args. supper().encode finally will call convert_tokens_to_string and _convert_id_to_token.
+        if len(kwargs) > 0:
+            return super().decode(token_ids, **kwargs)
+
+        if type(token_ids) is int:
+            token_ids = [token_ids]
+
+        return self.model.decode(cast(List[int], token_ids))
+
+    @staticmethod
+    def _split_whitespaces_or_nonwhitespaces(
+        s: str, max_consecutive_slice_len: int
+    ) -> Iterator[str]:
+        """
+        Splits the string `s` so that each substring contains no more than `max_consecutive_slice_len`
+        consecutive whitespaces or consecutive non-whitespaces.
+        """
+        current_slice_len = 0
+        current_slice_is_space = s[0].isspace() if len(s) > 0 else False
+        slice_start = 0
+
+        for i in range(len(s)):
+            is_now_space = s[i].isspace()
+
+            if current_slice_is_space ^ is_now_space:
+                current_slice_len = 1
+                current_slice_is_space = is_now_space
+            else:
+                current_slice_len += 1
+                if current_slice_len > max_consecutive_slice_len:
+                    yield s[slice_start:i]
+                    slice_start = i
+                    current_slice_len = 1
+        yield s[slice_start:]
+
+
+    """ ----- Below are the abstract methods required by PreTrainedTokenizer ----- """
+    @property
+    def vocab_size(self) -> int:
+        return self.n_words
+    
+    def get_vocab(self) -> Dict[str, int]:
+        return self.encoder
+
+    def _tokenize(self, text: str, **kwargs) -> List[str]:
+        return [
+            self.decoder[t]
+            for t in self.encode(text)
+        ]
+    
+    def _convert_token_to_id(self, token: str) -> int:
+        return self.encoder.get(token, self.unk_id)
+
+    def _convert_id_to_token(self, index: int) -> str:
+        return self.decoder.get(index)
+
+    @staticmethod
+    def clean_up_tokenization(out_string: str) -> str:
+        return out_string
+
+    def convert_tokens_to_string(self, tokens: List[str]) -> str:
+        text = ''.join(tokens).replace(SPIECE_UNDERLINE, '')
+        text = bytearray([self.byte_decoder[c] for c in text]).decode('utf-8', 'replace')
+        return text
+    
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+
+        return (out_vocab_file,)

tokenizer_config.json

@@ -0,0 +1,97 @@
+{
+  "added_tokens_decoder": {
+    "163584": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163585": {
+      "content": "[EOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163586": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163587": {
+      "content": "<|im_user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163588": {
+      "content": "<|im_assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163594": {
+      "content": "<|im_system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163601": {
+      "content": "<|im_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163838": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163839": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_user|>",
+    "<|im_assistant|>",
+    "<|im_system|>",
+    "<|im_middle|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_moonshot.TikTokenTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "extra_special_tokens": {},
+  "model_max_length": 1048576,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TikTokenTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.json

@@ -0,0 +1,14 @@
+{
+  "model": "kimi_k2",
+  "optimizer": "muon",
+  "lr": 0.02,
+  "wd": 0.1,
+  "dataset": "loggenix-rca",
+  "hidden_size": 1024,
+  "epochs": 1,
+  "save_path": "./trained_model",
+  "push_to_hub": true,
+  "repo_name": "kshitijthakkar/loggenix-nanoKimi2-test",
+  "hf_token": "hf_token",
+  "run_inference": true
+}