Upload folder using huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- code
+license: llama2
+tags:
+- llama-2
+- mlx
+pipeline_tag: text-generation
+---
+
+# mlx-community/CodeLlama-34b-Instruct-hf-4bit
+This model was converted to MLX format from [`codellama/CodeLlama-34b-Instruct-hf`]().
+Refer to the [original model card](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/CodeLlama-34b-Instruct-hf-4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,86 @@
+{
+    "vocab_size": 32000,
+    "max_position_embeddings": 16384,
+    "hidden_size": 8192,
+    "intermediate_size": 22016,
+    "num_hidden_layers": 48,
+    "num_attention_heads": 64,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 1000000,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": null,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/socialkeyboard/.cache/huggingface/hub/models--codellama--CodeLlama-34b-Instruct-hf/snapshots/cebb11eacbeecb9189e910d57a8faeadb949978f",
+    "transformers_version": "4.37.2",
+    "model_type": "llama",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58895b8978bda0f17f67d0a59050b54879ed747e14c11a605f572d8b3c7f8b68
+size 5281054892

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a5c1990e9f17027d006d6de212e03748b33e2e0f1dbf2a8b02e8c4997ac6c1
+size 5365533452

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682e3b7f928d9ac5e6987b09c3ea2cc35f644ff0b2e3fb9ed183fa8cd97e7df7
+size 5348986422

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51928af2e29e8325d25c1660f2e51a8fb84b90f5bf062fee9643ac48f9ac49a3
+size 3363509787

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenization_arcade100k.py

@@ -0,0 +1,292 @@
+# coding=utf-8
+# Copyright (c) 2023 Alibaba Cloud & Stability AI.
+#
+# Tongyi Qianwen LICENSE AGREEMENT:
+# https://github.com/QwenLM/Qwen/blob/5aa84bdfd3237b37f01bc88cd49b3279b9a71d0b/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
+"""Tokenization classes for Arcade100k."""
+
+import base64
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers.utils import logging
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "arcade100k.tiktoken"}
+NAME = "arcade100k"
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+ENDOFTEXT = "<|endoftext|>"
+FIM = [
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+]
+# `StarCoder` Tokens
+CODE = [
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+]
+CHAT = [
+    "<|im_start|>",  # Chat: Input message start
+    "<|im_end|>",  # Chat: Input message end
+]
+PAUSE = "<|pause|>"  # Think before you speak (https://arxiv.org/abs/2310.02226)
+REGISTERS = [
+    f"<|reg{i}|>" for i in range(0, 8)
+]  # Register 0 sink token (https://arxiv.org/abs/2309.17453)
+ENDOFPROMPT = "<|endofprompt|>"
+SPECIAL_TOKENS_NAMES = (
+    [ENDOFTEXT]
+    + FIM
+    + CODE
+    + [ENDOFPROMPT]
+    + CHAT
+    + [PAUSE]
+    + REGISTERS
+    + ["<|extra0|>"]
+)
+START_ID = 100257
+SPECIAL_TOKENS = {t: START_ID + i for i, t in enumerate(SPECIAL_TOKENS_NAMES)}
+
+
+def _arcade100k(vocab_file: str):
+    mergeable_ranks = _load_tiktoken_bpe(vocab_file)
+
+    return {
+        "name": NAME,
+        "pat_str": r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+""",
+        "mergeable_ranks": mergeable_ranks,
+        "special_tokens": SPECIAL_TOKENS,
+    }
+
+
+class Arcade100kTokenizer(PreTrainedTokenizer):
+    """
+    Construct a Arcade100k tokenizer backed by `tiktoken`.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+        errors (`str`, *optional*, defaults to `"replace"`):
+            How to handle errors in decoding UTF-8 byte sequences.
+            WARNING: the default behaviour of this function is lossy, since decoded bytes are not
+            guaranteed to be valid UTF-8. You can control this behaviour using the `errors` parameter,
+            for instance, setting `errors=strict`.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file: str,
+        errors: str = "replace",
+        **kwargs,
+    ):
+        super().__init__(errors=errors, **kwargs)
+        self.errors = errors
+
+        self._tiktoken_config = _arcade100k(vocab_file)
+        self.tokenizer = tiktoken.Encoding(**self._tiktoken_config)
+
+        # TODO: Remove this assertion
+        assert (
+            len(self.tokenizer._mergeable_ranks)
+            + len(self.tokenizer._special_tokens)
+            + 1
+            == self.tokenizer.n_vocab
+        ), f"{len(self.tokenizer._mergeable_ranks) + len(self.tokenizer._special_tokens)} != {self.tokenizer.n_vocab} in encoding"
+
+        self.decoder = {i: n for n, i in self.tokenizer._mergeable_ranks.items()}
+        self.decoder.update({i: n for n, i in self.tokenizer._special_tokens.items()})
+        # Provide default `eos_token` and `pad_token`
+        if self.eos_token is None:
+            self.eos_token = self.decoder[self.tokenizer.eot_token]
+        if self.pad_token is None:
+            self.pad_token = self.decoder[self.tokenizer.pad_token]
+
+        # Expose for convenience
+        self.mergeable_ranks = self.tokenizer._mergeable_ranks
+        self.special_tokens = self.tokenizer._special_tokens
+
+    def __len__(self):
+        return self.tokenizer.n_vocab
+
+    def __getstate__(self):
+        # Required for `pickle` support
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        self.__dict__.update(state)
+        self.tokenizer = tiktoken.Encoding(**self._tiktoken_config)
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.tokenizer._mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.tokenizer._special_tokens:
+                return self.tokenizer._special_tokens[tokens]
+            else:
+                return self.tokenizer._mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.tokenizer._special_tokens:
+                ids.append(self.tokenizer._special_tokens[token])
+            else:
+                ids.append(self.tokenizer._mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "arcade100k.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.tokenizer._mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.tokenizer._special_tokens:
+            return self.tokenizer._special_tokens[token]
+        if token in self.tokenizer._mergeable_ranks:
+            return self.tokenizer._mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.tokenizer.eot_token]
+        return self.tokenizer.decode(token_ids)

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

weights.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4a5fa26a83e9bada9f524000c663859a4cb8ccbabc4e05d7f89bb796cbba4e
+size 3289069095