bigdl-core-cpp 2.5.0b20240728__py3-none-win_amd64.whl → 2.5.0b20240730__py3-none-win_amd64.whl

bigdl/cpp/gguf-py/gguf/metadata.py

@@ -0,0 +1,503 @@
+from __future__ import annotations
+
+import re
+import json
+import yaml
+import logging
+from pathlib import Path
+from typing import Any, Literal, Optional
+from dataclasses import dataclass
+
+from .constants import Keys
+
+import gguf
+
+logger = logging.getLogger("metadata")
+
+
+@dataclass
+class Metadata:
+    # Authorship Metadata to be written to GGUF KV Store
+    name: Optional[str] = None
+    author: Optional[str] = None
+    version: Optional[str] = None
+    organization: Optional[str] = None
+    finetune: Optional[str] = None
+    basename: Optional[str] = None
+    description: Optional[str] = None
+    quantized_by: Optional[str] = None
+    size_label: Optional[str] = None
+    url: Optional[str] = None
+    doi: Optional[str] = None
+    uuid: Optional[str] = None
+    repo_url: Optional[str] = None
+    source_url: Optional[str] = None
+    source_doi: Optional[str] = None
+    source_uuid: Optional[str] = None
+    source_repo_url: Optional[str] = None
+    license: Optional[str] = None
+    license_name: Optional[str] = None
+    license_link: Optional[str] = None
+    base_models: Optional[list[dict]] = None
+    tags: Optional[list[str]] = None
+    languages: Optional[list[str]] = None
+    datasets: Optional[list[str]] = None
+
+    @staticmethod
+    def load(metadata_override_path: Optional[Path] = None, model_path: Optional[Path] = None, model_name: Optional[str] = None, total_params: int = 0) -> Metadata:
+        # This grabs as many contextual authorship metadata as possible from the model repository
+        # making any conversion as required to match the gguf kv store metadata format
+        # as well as giving users the ability to override any authorship metadata that may be incorrect
+
+        # Create a new Metadata instance
+        metadata = Metadata()
+
+        model_card = Metadata.load_model_card(model_path)
+        hf_params = Metadata.load_hf_parameters(model_path)
+        # TODO: load adapter_config.json when possible, it usually contains the base model of the LoRA adapter
+
+        # heuristics
+        metadata = Metadata.apply_metadata_heuristic(metadata, model_card, hf_params, model_path, total_params)
+
+        # Metadata Override File Provided
+        # This is based on LLM_KV_NAMES mapping in llama.cpp
+        metadata_override = Metadata.load_metadata_override(metadata_override_path)
+
+        metadata.name            = metadata_override.get(Keys.General.NAME,            metadata.name)
+        metadata.author          = metadata_override.get(Keys.General.AUTHOR,          metadata.author)
+        metadata.version         = metadata_override.get(Keys.General.VERSION,         metadata.version)
+        metadata.organization    = metadata_override.get(Keys.General.ORGANIZATION,    metadata.organization)
+
+        metadata.finetune        = metadata_override.get(Keys.General.FINETUNE,        metadata.finetune)
+        metadata.basename        = metadata_override.get(Keys.General.BASENAME,        metadata.basename)
+
+        metadata.description     = metadata_override.get(Keys.General.DESCRIPTION,     metadata.description)
+        metadata.quantized_by    = metadata_override.get(Keys.General.QUANTIZED_BY,    metadata.quantized_by)
+
+        metadata.size_label      = metadata_override.get(Keys.General.SIZE_LABEL,      metadata.size_label)
+        metadata.license_name    = metadata_override.get(Keys.General.LICENSE_NAME,    metadata.license_name)
+        metadata.license_link    = metadata_override.get(Keys.General.LICENSE_LINK,    metadata.license_link)
+
+        metadata.url             = metadata_override.get(Keys.General.URL,             metadata.url)
+        metadata.doi             = metadata_override.get(Keys.General.DOI,             metadata.doi)
+        metadata.uuid            = metadata_override.get(Keys.General.UUID,            metadata.uuid)
+        metadata.repo_url        = metadata_override.get(Keys.General.REPO_URL,        metadata.repo_url)
+
+        metadata.source_url      = metadata_override.get(Keys.General.SOURCE_URL,      metadata.source_url)
+        metadata.source_doi      = metadata_override.get(Keys.General.SOURCE_DOI,      metadata.source_doi)
+        metadata.source_uuid     = metadata_override.get(Keys.General.SOURCE_UUID,     metadata.source_uuid)
+        metadata.source_repo_url = metadata_override.get(Keys.General.SOURCE_REPO_URL, metadata.source_repo_url)
+
+        # Base Models is received here as an array of models
+        metadata.base_models     = metadata_override.get("general.base_models",        metadata.base_models)
+
+        metadata.tags            = metadata_override.get(Keys.General.TAGS,            metadata.tags)
+        metadata.languages       = metadata_override.get(Keys.General.LANGUAGES,       metadata.languages)
+        metadata.datasets        = metadata_override.get(Keys.General.DATASETS,        metadata.datasets)
+
+        # Direct Metadata Override (via direct cli argument)
+        if model_name is not None:
+            metadata.name = model_name
+
+        return metadata
+
+    @staticmethod
+    def load_metadata_override(metadata_override_path: Optional[Path] = None) -> dict[str, Any]:
+        if metadata_override_path is None or not metadata_override_path.is_file():
+            return {}
+
+        with open(metadata_override_path, "r", encoding="utf-8") as f:
+            return json.load(f)
+
+    @staticmethod
+    def load_model_card(model_path: Optional[Path] = None) -> dict[str, Any]:
+        if model_path is None or not model_path.is_dir():
+            return {}
+
+        model_card_path = model_path / "README.md"
+
+        if not model_card_path.is_file():
+            return {}
+
+        # The model card metadata is assumed to always be in YAML
+        # ref: https://github.com/huggingface/transformers/blob/a5c642fe7a1f25d3bdcd76991443ba6ff7ee34b2/src/transformers/modelcard.py#L468-L473
+        with open(model_card_path, "r", encoding="utf-8") as f:
+            if f.readline() == "---\n":
+                raw = f.read().partition("---\n")[0]
+                data = yaml.safe_load(raw)
+                if isinstance(data, dict):
+                    return data
+                else:
+                    logger.error(f"while reading YAML model card frontmatter, data is {type(data)} instead of dict")
+                    return {}
+            else:
+                return {}
+
+    @staticmethod
+    def load_hf_parameters(model_path: Optional[Path] = None) -> dict[str, Any]:
+        if model_path is None or not model_path.is_dir():
+            return {}
+
+        config_path = model_path / "config.json"
+
+        if not config_path.is_file():
+            return {}
+
+        with open(config_path, "r", encoding="utf-8") as f:
+            return json.load(f)
+
+    @staticmethod
+    def id_to_title(string):
+        # Convert capitalization into title form unless acronym or version number
+        return ' '.join([w.title() if w.islower() and not re.match(r'^(v\d+(?:\.\d+)*|\d.*)$', w) else w for w in string.strip().replace('-', ' ').split()])
+
+    @staticmethod
+    def get_model_id_components(model_id: Optional[str] = None, total_params: int = 0) -> tuple[str | None, str | None, str | None, str | None, str | None, str | None]:
+        # Huggingface often store model id as '<org>/<model name>'
+        # so let's parse it and apply some heuristics if possible for model name components
+
+        if model_id is None:
+            # model ID missing
+            return None, None, None, None, None, None
+
+        if ' ' in model_id:
+            # model ID is actually a normal human sentence
+            # which means its most likely a normal model name only
+            # not part of the hugging face naming standard, but whatever
+            return model_id, None, None, None, None, None
+
+        if '/' in model_id:
+            # model ID (huggingface style)
+            org_component, model_full_name_component = model_id.split('/', 1)
+        else:
+            # model ID but missing org components
+            org_component, model_full_name_component = None, model_id
+
+        # Check if we erroneously matched against './' or '../' etc...
+        if org_component is not None and org_component[0] == '.':
+            org_component = None
+
+        name_parts: list[str] = model_full_name_component.split('-')
+
+        # Remove empty parts
+        for i in reversed(range(len(name_parts))):
+            if len(name_parts[i]) == 0:
+                del name_parts[i]
+
+        name_types: list[
+            set[Literal["basename", "size_label", "finetune", "version", "type"]]
+        ] = [set() for _ in name_parts]
+
+        # Annotate the name
+        for i, part in enumerate(name_parts):
+            # Version
+            if re.fullmatch(r'(v|iter)?\d+([.]\d+)*', part, re.IGNORECASE):
+                name_types[i].add("version")
+            # Quant type (should not be there for base models, but still annotated)
+            elif re.fullmatch(r'i?q\d(_\w)*|b?fp?(16|32)', part, re.IGNORECASE):
+                name_types[i].add("type")
+                name_parts[i] = part.upper()
+            # Model size
+            elif i > 0 and re.fullmatch(r'(([A]|\d+[x])?\d+([._]\d+)?[KMBT][\d]?|small|mini|medium|large|x?xl)', part, re.IGNORECASE):
+                part = part.replace("_", ".")
+                # Handle weird bloom-7b1 notation
+                if part[-1].isdecimal():
+                    part = part[:-2] + "." + part[-1] + part[-2]
+                # Normalize the size suffixes
+                if len(part) > 1 and part[-2].isdecimal():
+                    if part[-1] in "kmbt":
+                        part = part[:-1] + part[-1].upper()
+                if total_params != 0:
+                    try:
+                        label_params = float(part[:-1]) * pow(1000, " KMBT".find(part[-1]))
+                        # Only use it as a size label if it's close or bigger than the model size
+                        # Note that LoRA adapters don't necessarily include all layers,
+                        # so this is why bigger label sizes are accepted.
+                        # Do not use the size label when it's smaller than 1/8 of the model size
+                        if (total_params < 0 and label_params < abs(total_params) // 8) or (
+                            # Check both directions when the current model isn't a LoRA adapter
+                            total_params > 0 and abs(label_params - total_params) > 7 * total_params // 8
+                        ):
+                            # Likely a context length
+                            name_types[i].add("finetune")
+                            # Lowercase the size when it's a context length
+                            part = part[:-1] + part[-1].lower()
+                    except ValueError:
+                        # Failed to convert the size label to float, use it anyway
+                        pass
+                if len(name_types[i]) == 0:
+                    name_types[i].add("size_label")
+                name_parts[i] = part
+            # Some easy to recognize finetune names
+            elif i > 0 and re.fullmatch(r'chat|instruct|vision|lora', part, re.IGNORECASE):
+                if total_params < 0 and part.lower() == "lora":
+                    # ignore redundant "lora" in the finetune part when the output is a lora adapter
+                    name_types[i].add("type")
+                else:
+                    name_types[i].add("finetune")
+
+        # Ignore word-based size labels when there is at least a number-based one present
+        # TODO: should word-based size labels always be removed instead?
+        if any(c.isdecimal() for n, t in zip(name_parts, name_types) if "size_label" in t for c in n):
+            for n, t in zip(name_parts, name_types):
+                if "size_label" in t:
+                    if all(c.isalpha() for c in n):
+                        t.remove("size_label")
+
+        at_start = True
+        # Find the basename through the annotated name
+        for part, t in zip(name_parts, name_types):
+            if at_start and ((len(t) == 0 and part[0].isalpha()) or "version" in t):
+                t.add("basename")
+            else:
+                if at_start:
+                    at_start = False
+                if len(t) == 0:
+                    t.add("finetune")
+
+        # Remove the basename annotation from trailing version
+        for part, t in zip(reversed(name_parts), reversed(name_types)):
+            if "basename" in t and len(t) > 1:
+                t.remove("basename")
+            else:
+                break
+
+        basename = "-".join(n for n, t in zip(name_parts, name_types) if "basename" in t) or None
+        # Deduplicate size labels using order-preserving 'dict' ('set' seems to sort the keys)
+        size_label = "-".join(dict.fromkeys(s for s, t in zip(name_parts, name_types) if "size_label" in t).keys()) or None
+        finetune = "-".join(f for f, t in zip(name_parts, name_types) if "finetune" in t) or None
+        # TODO: should the basename version always be excluded?
+        # NOTE: multiple finetune versions are joined together
+        version = "-".join(v for v, t, in zip(name_parts, name_types) if "version" in t and "basename" not in t) or None
+
+        if size_label is None and finetune is None and version is None:
+            # Too ambiguous, output nothing
+            basename = None
+
+        return model_full_name_component, org_component, basename, finetune, version, size_label
+
+    @staticmethod
+    def apply_metadata_heuristic(metadata: Metadata, model_card: Optional[dict] = None, hf_params: Optional[dict] = None, model_path: Optional[Path] = None, total_params: int = 0) -> Metadata:
+        # Reference Model Card Metadata: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
+
+        # Model Card Heuristics
+        ########################
+        if model_card is not None:
+
+            if "model_name" in model_card and metadata.name is None:
+                # Not part of huggingface model card standard but notice some model creator using it
+                # such as TheBloke in 'TheBloke/Mistral-7B-Instruct-v0.2-GGUF'
+                metadata.name = model_card.get("model_name")
+
+            if "model_creator" in model_card and metadata.author is None:
+                # Not part of huggingface model card standard but notice some model creator using it
+                # such as TheBloke in 'TheBloke/Mistral-7B-Instruct-v0.2-GGUF'
+                metadata.author = model_card.get("model_creator")
+
+            if "model_type" in model_card and metadata.basename is None:
+                # Not part of huggingface model card standard but notice some model creator using it
+                # such as TheBloke in 'TheBloke/Mistral-7B-Instruct-v0.2-GGUF'
+                metadata.basename = model_card.get("model_type")
+
+            if "base_model" in model_card:
+                # This represents the parent models that this is based on
+                # Example: stabilityai/stable-diffusion-xl-base-1.0. Can also be a list (for merges)
+                # Example of merges: https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1/blob/main/README.md
+                metadata_base_models = []
+                base_model_value = model_card.get("base_model", None)
+
+                if base_model_value is not None:
+                    if isinstance(base_model_value, str):
+                        metadata_base_models.append(base_model_value)
+                    elif isinstance(base_model_value, list):
+                        metadata_base_models.extend(base_model_value)
+
+                if metadata.base_models is None:
+                    metadata.base_models = []
+
+                for model_id in metadata_base_models:
+                    # NOTE: model size of base model is assumed to be similar to the size of the current model
+                    model_full_name_component, org_component, basename, finetune, version, size_label = Metadata.get_model_id_components(model_id, total_params)
+                    base_model = {}
+                    if model_full_name_component is not None:
+                        base_model["name"] = Metadata.id_to_title(model_full_name_component)
+                    if org_component is not None:
+                        base_model["organization"] = Metadata.id_to_title(org_component)
+                    if version is not None:
+                        base_model["version"] = version
+                    if org_component is not None and model_full_name_component is not None:
+                        base_model["repo_url"] = f"https://huggingface.co/{org_component}/{model_full_name_component}"
+                    metadata.base_models.append(base_model)
+
+            if "license" in model_card and metadata.license is None:
+                metadata.license = model_card.get("license")
+
+            if "license_name" in model_card and metadata.license_name is None:
+                metadata.license_name = model_card.get("license_name")
+
+            if "license_link" in model_card and metadata.license_link is None:
+                metadata.license_link = model_card.get("license_link")
+
+            tags_value = model_card.get("tags", None)
+            if tags_value is not None:
+
+                if metadata.tags is None:
+                    metadata.tags = []
+
+                if isinstance(tags_value, str):
+                    metadata.tags.append(tags_value)
+                elif isinstance(tags_value, list):
+                    metadata.tags.extend(tags_value)
+
+            pipeline_tags_value = model_card.get("pipeline_tag", None)
+            if pipeline_tags_value is not None:
+
+                if metadata.tags is None:
+                    metadata.tags = []
+
+                if isinstance(pipeline_tags_value, str):
+                    metadata.tags.append(pipeline_tags_value)
+                elif isinstance(pipeline_tags_value, list):
+                    metadata.tags.extend(pipeline_tags_value)
+
+            language_value = model_card.get("languages", model_card.get("language", None))
+            if language_value is not None:
+
+                if metadata.languages is None:
+                    metadata.languages = []
+
+                if isinstance(language_value, str):
+                    metadata.languages.append(language_value)
+                elif isinstance(language_value, list):
+                    metadata.languages.extend(language_value)
+
+            dataset_value = model_card.get("datasets", model_card.get("dataset", None))
+            if dataset_value is not None:
+
+                if metadata.datasets is None:
+                    metadata.datasets = []
+
+                if isinstance(dataset_value, str):
+                    metadata.datasets.append(dataset_value)
+                elif isinstance(dataset_value, list):
+                    metadata.datasets.extend(dataset_value)
+
+        # Hugging Face Parameter Heuristics
+        ####################################
+
+        if hf_params is not None:
+
+            hf_name_or_path = hf_params.get("_name_or_path")
+            if hf_name_or_path is not None and hf_name_or_path.count('/') <= 1:
+                # Use _name_or_path only if its actually a model name and not some computer path
+                # e.g. 'meta-llama/Llama-2-7b-hf'
+                model_id = hf_name_or_path
+                model_full_name_component, org_component, basename, finetune, version, size_label = Metadata.get_model_id_components(model_id, total_params)
+                if metadata.name is None and model_full_name_component is not None:
+                    metadata.name = Metadata.id_to_title(model_full_name_component)
+                if metadata.organization is None and org_component is not None:
+                    metadata.organization = Metadata.id_to_title(org_component)
+                if metadata.basename is None and basename is not None:
+                    metadata.basename = basename
+                if metadata.finetune is None and finetune is not None:
+                    metadata.finetune = finetune
+                if metadata.version is None and version is not None:
+                    metadata.version = version
+                if metadata.size_label is None and size_label is not None:
+                    metadata.size_label = size_label
+
+        # Directory Folder Name Fallback Heuristics
+        ############################################
+        if model_path is not None:
+            model_id = model_path.name
+            model_full_name_component, org_component, basename, finetune, version, size_label = Metadata.get_model_id_components(model_id, total_params)
+            if metadata.name is None and model_full_name_component is not None:
+                metadata.name = Metadata.id_to_title(model_full_name_component)
+            if metadata.organization is None and org_component is not None:
+                metadata.organization = Metadata.id_to_title(org_component)
+            if metadata.basename is None and basename is not None:
+                metadata.basename = basename
+            if metadata.finetune is None and finetune is not None:
+                metadata.finetune = finetune
+            if metadata.version is None and version is not None:
+                metadata.version = version
+            if metadata.size_label is None and size_label is not None:
+                metadata.size_label = size_label
+
+        return metadata
+
+    def set_gguf_meta_model(self, gguf_writer: gguf.GGUFWriter):
+        assert self.name is not None
+        gguf_writer.add_name(self.name)
+
+        if self.author is not None:
+            gguf_writer.add_author(self.author)
+        if self.version is not None:
+            gguf_writer.add_version(self.version)
+        if self.organization is not None:
+            gguf_writer.add_organization(self.organization)
+
+        if self.finetune is not None:
+            gguf_writer.add_finetune(self.finetune)
+        if self.basename is not None:
+            gguf_writer.add_basename(self.basename)
+
+        if self.description is not None:
+            gguf_writer.add_description(self.description)
+        if self.quantized_by is not None:
+            gguf_writer.add_quantized_by(self.quantized_by)
+
+        if self.size_label is not None:
+            gguf_writer.add_size_label(self.size_label)
+
+        if self.license is not None:
+            gguf_writer.add_license(self.license)
+        if self.license_name is not None:
+            gguf_writer.add_license_name(self.license_name)
+        if self.license_link is not None:
+            gguf_writer.add_license_link(self.license_link)
+
+        if self.url is not None:
+            gguf_writer.add_url(self.url)
+        if self.doi is not None:
+            gguf_writer.add_doi(self.doi)
+        if self.uuid is not None:
+            gguf_writer.add_uuid(self.uuid)
+        if self.repo_url is not None:
+            gguf_writer.add_repo_url(self.repo_url)
+
+        if self.source_url is not None:
+            gguf_writer.add_source_url(self.source_url)
+        if self.source_doi is not None:
+            gguf_writer.add_source_doi(self.source_doi)
+        if self.source_uuid is not None:
+            gguf_writer.add_source_uuid(self.source_uuid)
+        if self.source_repo_url is not None:
+            gguf_writer.add_source_repo_url(self.source_repo_url)
+
+        if self.base_models is not None:
+            gguf_writer.add_base_model_count(len(self.base_models))
+            for key, base_model_entry in enumerate(self.base_models):
+                if "name" in base_model_entry:
+                    gguf_writer.add_base_model_name(key, base_model_entry["name"])
+                if "author" in base_model_entry:
+                    gguf_writer.add_base_model_author(key, base_model_entry["author"])
+                if "version" in base_model_entry:
+                    gguf_writer.add_base_model_version(key, base_model_entry["version"])
+                if "organization" in base_model_entry:
+                    gguf_writer.add_base_model_organization(key, base_model_entry["organization"])
+                if "url" in base_model_entry:
+                    gguf_writer.add_base_model_url(key, base_model_entry["url"])
+                if "doi" in base_model_entry:
+                    gguf_writer.add_base_model_doi(key, base_model_entry["doi"])
+                if "uuid" in base_model_entry:
+                    gguf_writer.add_base_model_uuid(key, base_model_entry["uuid"])
+                if "repo_url" in base_model_entry:
+                    gguf_writer.add_base_model_repo_url(key, base_model_entry["repo_url"])
+
+        if self.tags is not None:
+            gguf_writer.add_tags(self.tags)
+        if self.languages is not None:
+            gguf_writer.add_languages(self.languages)
+        if self.datasets is not None:
+            gguf_writer.add_datasets(self.datasets)

bigdl/cpp/gguf-py/gguf/utility.py

@@ -0,0 +1,69 @@
+from __future__ import annotations
+
+from typing import Literal
+
+
+def fill_templated_filename(filename: str, output_type: str | None) -> str:
+    # Given a file name fill in any type templates e.g. 'some-model-name.{ftype}.gguf'
+    ftype_lowercase: str = output_type.lower() if output_type is not None else ""
+    ftype_uppercase: str = output_type.upper() if output_type is not None else ""
+    return filename.format(ftype_lowercase,
+                           outtype=ftype_lowercase, ftype=ftype_lowercase,
+                           OUTTYPE=ftype_uppercase, FTYPE=ftype_uppercase)
+
+
+def model_weight_count_rounded_notation(model_params_count: int, min_digits: int = 2) -> str:
+    if model_params_count > 1e12 :
+        # Trillions Of Parameters
+        scaled_model_params = model_params_count * 1e-12
+        scale_suffix = "T"
+    elif model_params_count > 1e9 :
+        # Billions Of Parameters
+        scaled_model_params = model_params_count * 1e-9
+        scale_suffix = "B"
+    elif model_params_count > 1e6 :
+        # Millions Of Parameters
+        scaled_model_params = model_params_count * 1e-6
+        scale_suffix = "M"
+    else:
+        # Thousands Of Parameters
+        scaled_model_params = model_params_count * 1e-3
+        scale_suffix = "K"
+
+    fix = max(min_digits - len(str(round(scaled_model_params)).lstrip('0')), 0)
+
+    return f"{scaled_model_params:.{fix}f}{scale_suffix}"
+
+
+def size_label(total_params: int, shared_params: int, expert_params: int, expert_count: int) -> str:
+
+    if expert_count > 0:
+        pretty_size = model_weight_count_rounded_notation(abs(shared_params) + abs(expert_params), min_digits=2)
+        size_class = f"{expert_count}x{pretty_size}"
+    else:
+        size_class = model_weight_count_rounded_notation(abs(total_params), min_digits=2)
+
+    return size_class
+
+
+def naming_convention(model_name: str | None, base_name: str | None, finetune_string: str | None, version_string: str | None, size_label: str | None, output_type: str | None, model_type: Literal['vocab', 'LoRA'] | None = None) -> str:
+    # Reference: https://github.com/ggerganov/ggml/blob/master/docs/gguf.md#gguf-naming-convention
+
+    if base_name is not None:
+        name = base_name.strip().replace(' ', '-').replace('/', '-')
+    elif model_name is not None:
+        name = model_name.strip().replace(' ', '-').replace('/', '-')
+    else:
+        name = "ggml-model"
+
+    parameters = f"-{size_label}" if size_label is not None else ""
+
+    finetune = f"-{finetune_string.strip().replace(' ', '-')}" if finetune_string is not None else ""
+
+    version = f"-{version_string.strip().replace(' ', '-')}" if version_string is not None else ""
+
+    encoding = f"-{output_type.strip().replace(' ', '-').upper()}" if output_type is not None else ""
+
+    kind = f"-{model_type.strip().replace(' ', '-')}" if model_type is not None else ""
+
+    return f"{name}{parameters}{finetune}{version}{encoding}{kind}"

{bigdl_core_cpp-2.5.0b20240728.dist-info → bigdl_core_cpp-2.5.0b20240730.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bigdl-core-cpp
-Version: 2.5.0b20240728
+Version: 2.5.0b20240730
 Summary: Large Language Model Develop Toolkit
 Author: BigDL Authors
 License: Apache License, Version 2.0

bigdl_core_cpp-2.5.0b20240730.dist-info/RECORD

@@ -0,0 +1,63 @@
+bigdl/cpp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bigdl/cpp/convert-hf-to-gguf.py,sha256=VxIE_ouOPHiueEpvh6KBL-B9IFFE1yy8jVe_cdhaJeo,170360
+bigdl/cpp/convert.py,sha256=AAjyH5aqwEFkChWzwUUYTpqOfUnbdx8uNtDka-rP9Vw,71131
+bigdl/cpp/gguf-py/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bigdl/cpp/gguf-py/gguf/__init__.py,sha256=DjP96RH9gKUnDP8hy6S_kz-ALA26v-58fp1lExmSOxg,226
+bigdl/cpp/gguf-py/gguf/constants.py,sha256=oDFc2pFp-U_B0U2D9BgHerKoYeFFEXGEYaM8SX8UNfI,48230
+bigdl/cpp/gguf-py/gguf/gguf.py,sha256=V5jY968TEJn6GJHVdjzH0_aIkZ1QC967vPdHDKDoxZw,491
+bigdl/cpp/gguf-py/gguf/gguf_reader.py,sha256=N3LnQQ30t-S0U85-EvZZzIBfHzo0XuyFVUltdg7Sj3c,12680
+bigdl/cpp/gguf-py/gguf/gguf_writer.py,sha256=9O_6lnFgywy_ArIeKxiAHtgOA4_vTJ-PUPgHZbvI6q8,35484
+bigdl/cpp/gguf-py/gguf/lazy.py,sha256=SFRlFuNlBdhn4rdbTcooo1avWk-tIh9tEufhbTCXFHM,8737
+bigdl/cpp/gguf-py/gguf/metadata.py,sha256=MeMgNeKzhxjcpbe1WOkuIJiTR99PyKAgPsZ24AFsT7Y,25353
+bigdl/cpp/gguf-py/gguf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bigdl/cpp/gguf-py/gguf/quants.py,sha256=KrA_NtxRSfYq9PQVn9qn9X6pIXFJa0E1hziheYNolp0,4477
+bigdl/cpp/gguf-py/gguf/tensor_mapping.py,sha256=aFaLvDjJiVH22o7qaESTWZw9F3tCraLVM08bpLJA5zc,30795
+bigdl/cpp/gguf-py/gguf/utility.py,sha256=ceoMg4u13i6bvZUVGTsOAWZwKjqKnSj7QLeAMTiYNFY,3001
+bigdl/cpp/gguf-py/gguf/vocab.py,sha256=0_n5lD3w2skafTJGQOZaP3mo4Wh_CNXJVuoe6FmX8-E,7012
+bigdl/cpp/libs/baby-llama.exe,sha256=8g2v072sbfELZYAelJt8aHFc0gIwSOFbvPjHZnbwx78,200192
+bigdl/cpp/libs/batched-bench.exe,sha256=k2X56t9_YcJo3I0ilvxKlOiSPHl4bbwUFtd1axWyKq0,206848
+bigdl/cpp/libs/batched.exe,sha256=FbKp5iTbL49xKwYwC0cNC_Ey-ckFGyS0EbUw25JRQUY,208896
+bigdl/cpp/libs/beam-search.exe,sha256=im0DrwTO_8wd9_19Yb9oZegZJWlqZ2z0XsSsxc6aElo,214528
+bigdl/cpp/libs/benchmark.exe,sha256=taZ3aoVzZ0f10KcwqOEGiGc8mI0iX2jUxFTrAGZSNrU,74240
+bigdl/cpp/libs/common.lib,sha256=G4DvnW7eppABP9SSyE_hCvCWxf5lY12Kyb1GEwTZWF0,3330124
+bigdl/cpp/libs/convert-llama2c-to-ggml.exe,sha256=3QEMHd-KZkpHF2186qxrk-PtqGj0HWgTmVxtbm-TwVs,126464
+bigdl/cpp/libs/embedding.exe,sha256=-zeiM-9ki_TujYF89_BVDKEX9uIBvcaaFxNOiFSAWPE,644096
+bigdl/cpp/libs/export-lora.exe,sha256=LdSXGvXK9wUJZ9GUL1sY097CenKPRXMds7lXCXG_zZ0,90112
+bigdl/cpp/libs/finetune.exe,sha256=ufEWyZ4EZmwBCIISZv-ttjJWrNRabMqfL-8l48bky80,302592
+bigdl/cpp/libs/ggml_shared.dll,sha256=hIbB-RN_bKCo-4whlj9eIXDpRN1hY-y4AzKBMDxUKVA,6305280
+bigdl/cpp/libs/gguf.exe,sha256=CfrOrfJFaHQuG2UdcdgXYD5jQqqmnDtLriQnRz29Pds,5817856
+bigdl/cpp/libs/gritlm.exe,sha256=XiXIaqPPJ7ydsVBh9x-dINarkQKF8L9ustJa-fr1zu8,638464
+bigdl/cpp/libs/imatrix.exe,sha256=7Up8faMnkOQkKoEJA-CswzWCLZcN_uFBuWOS3PLtj6o,676352
+bigdl/cpp/libs/infill.exe,sha256=FRbpAFYCb3k49RWeY0BhRdEHJSMlXgWWz3MP2DIJoNM,733184
+bigdl/cpp/libs/llama-bench.exe,sha256=o8bmZ8FNDXUPskfQ-uPJOAqYfUFzLoqKQakqZ35LzLM,336384
+bigdl/cpp/libs/llama.dll,sha256=3gm0xqLF_IMGgwWuJNCimM0cW3SUlszRzlfz3zkloXQ,7926272
+bigdl/cpp/libs/llava-cli.exe,sha256=yjnUZgqfgmFw1nv-aWm1xhce4UoNYHq9ta8XTlmo7nU,921600
+bigdl/cpp/libs/llava_shared.dll,sha256=AJH-3DUDLLHf91jXKc-K1TbFp_nJyMRsKgFRxbbrKBs,6572544
+bigdl/cpp/libs/lookahead.exe,sha256=TIBmEa6cjFgn1zHRUFbI35Piij2jeDrXN31AjqzVqlM,684032
+bigdl/cpp/libs/lookup.exe,sha256=u-dKYllkYAtnvUWaVfGjcV7MpnFi4cWl_w2RZptFME8,718336
+bigdl/cpp/libs/ls-sycl-device.exe,sha256=t7RPsgiIH5YItG-AqgMh22eIaosJk61K5_HdCcTwNLM,10240
+bigdl/cpp/libs/main.exe,sha256=l5rW5U0UazduG66EJycQFEHM-J15QdrYBDI8_G_ScFg,764416
+bigdl/cpp/libs/ollama.exe,sha256=9YypM_2ba9gU--8CSRqLJKlFIRzL5jlKbMTo-CCWTso,64183875
+bigdl/cpp/libs/parallel.exe,sha256=tMTw3dU1Exat6FZKQY9U5lTrUYGXR6RPtT9xN77VeII,701440
+bigdl/cpp/libs/passkey.exe,sha256=m86xUJ0I4ra_2pJfRYh6YfcrPDeJx8pm-uYdt-Cti-Q,216064
+bigdl/cpp/libs/perplexity.exe,sha256=zj-iaPoiDx-T7L3Pst3AUqLTLO-iD8CC5eGfImFOmdU,782336
+bigdl/cpp/libs/q8dot.exe,sha256=h3WUcEZSZEYbokfdzlgNAQv24lVfsii9RoUZ6ddO0NU,53760
+bigdl/cpp/libs/quantize-stats.exe,sha256=8tKmXkOmLYHBsBMAhXCmNOFuwxWLBY__wYb1u8jXP0Q,130048
+bigdl/cpp/libs/quantize.exe,sha256=Su_jZm7xu4CTDC7sou2XmUR1wUozsnuD3lAKkLodEI8,235520
+bigdl/cpp/libs/save-load-state.exe,sha256=_a0nQ3P-PtPK65TcA7gpb-YGgufqCkdkY9S3bEjp8BI,636416
+bigdl/cpp/libs/server.exe,sha256=mAAMbVTzaMmN879bfBfIf0_8cgEKp5JLzepwGxfZlIE,1731584
+bigdl/cpp/libs/simple.exe,sha256=19IuLS9YCO6BJ3NJlysXEwuiHYmW4us8py5a8hK5Cvs,202752
+bigdl/cpp/libs/speculative.exe,sha256=FqSfP6gTvTBWkJzk8-bsNP8ooX7CjcjLFQQqr7v-8HY,709632
+bigdl/cpp/libs/tokenize.exe,sha256=3raRqVVUUf9kECy_kF30enKrCIERgoF37RMvAsSglc4,203264
+bigdl/cpp/libs/train-text-from-scratch.exe,sha256=aCXUDRZtYkul26NM22R72vAT74quwtZMO0tkHl2I5xc,283648
+bigdl/cpp/libs/vdot.exe,sha256=t4_Q2ntM7rYU6m7YYHLMiMzi8c3iNS3MmQ1L92a3Oxk,56320
+bigdl/cpp/libs/dist/windows-amd64/ollama_runners/cpu/ollama_llama_server.exe,sha256=2vMoPDzE462e6ifWu2e7taxq1SrkLuZQ34Bwreu6mTY,8601600
+bigdl/cpp/libs/dist/windows-amd64/ollama_runners/cpu_avx/ollama_llama_server.exe,sha256=T31F_8ucwNy3sbcriviVnz3UM7boOE1s3BpvdbBME-U,8601600
+bigdl/cpp/libs/dist/windows-amd64/ollama_runners/cpu_avx2/ollama_llama_server.exe,sha256=8zadvwqJcmhOhepRYML6Nmqs9jBJBO2LxnkWVhrppzs,8601600
+bigdl_core_cpp-2.5.0b20240730.data/scripts/init-llama-cpp.bat,sha256=13AgSYRyzk6hlSz11dPyCMJeSoW9z8PZ9l85E_5GWxs,528
+bigdl_core_cpp-2.5.0b20240730.data/scripts/init-llama-cpp.ps1,sha256=JFOylLxO4MKpllHhdbPuJ1xHi9azxDpzdJns8JtZpkU,501
+bigdl_core_cpp-2.5.0b20240730.data/scripts/init-ollama.bat,sha256=I2em4AnSSMq7LX3IRI3QR9w3UY2y2Y8zXQkpL09-G7w,472
+bigdl_core_cpp-2.5.0b20240730.dist-info/METADATA,sha256=2vRCowVqBksXFJvTvl2Ia6V95Ki-2PMnjxHAgNKI5pY,668
+bigdl_core_cpp-2.5.0b20240730.dist-info/WHEEL,sha256=at4xwl6JdXdkZHxdo5ixTwJ7ENtVftSy2wqmsdmo_4U,98
+bigdl_core_cpp-2.5.0b20240730.dist-info/top_level.txt,sha256=iGuLfZARD_qANcIMfy0tbbrC3EtCg6BSiH8icc3dLWs,6
+bigdl_core_cpp-2.5.0b20240730.dist-info/RECORD,,

bigdl_core_cpp-2.5.0b20240728.dist-info/RECORD

@@ -1,61 +0,0 @@
-bigdl/cpp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bigdl/cpp/convert-hf-to-gguf.py,sha256=VxIE_ouOPHiueEpvh6KBL-B9IFFE1yy8jVe_cdhaJeo,170360
-bigdl/cpp/convert.py,sha256=AAjyH5aqwEFkChWzwUUYTpqOfUnbdx8uNtDka-rP9Vw,71131
-bigdl/cpp/gguf-py/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bigdl/cpp/gguf-py/gguf/__init__.py,sha256=DjP96RH9gKUnDP8hy6S_kz-ALA26v-58fp1lExmSOxg,226
-bigdl/cpp/gguf-py/gguf/constants.py,sha256=oDFc2pFp-U_B0U2D9BgHerKoYeFFEXGEYaM8SX8UNfI,48230
-bigdl/cpp/gguf-py/gguf/gguf.py,sha256=V5jY968TEJn6GJHVdjzH0_aIkZ1QC967vPdHDKDoxZw,491
-bigdl/cpp/gguf-py/gguf/gguf_reader.py,sha256=N3LnQQ30t-S0U85-EvZZzIBfHzo0XuyFVUltdg7Sj3c,12680
-bigdl/cpp/gguf-py/gguf/gguf_writer.py,sha256=9O_6lnFgywy_ArIeKxiAHtgOA4_vTJ-PUPgHZbvI6q8,35484
-bigdl/cpp/gguf-py/gguf/lazy.py,sha256=SFRlFuNlBdhn4rdbTcooo1avWk-tIh9tEufhbTCXFHM,8737
-bigdl/cpp/gguf-py/gguf/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bigdl/cpp/gguf-py/gguf/quants.py,sha256=KrA_NtxRSfYq9PQVn9qn9X6pIXFJa0E1hziheYNolp0,4477
-bigdl/cpp/gguf-py/gguf/tensor_mapping.py,sha256=aFaLvDjJiVH22o7qaESTWZw9F3tCraLVM08bpLJA5zc,30795
-bigdl/cpp/gguf-py/gguf/vocab.py,sha256=0_n5lD3w2skafTJGQOZaP3mo4Wh_CNXJVuoe6FmX8-E,7012
-bigdl/cpp/libs/baby-llama.exe,sha256=XQag7QiC5jzVrQS6Q8gOOPjxjsC0idimDCe3wpJg1us,200192
-bigdl/cpp/libs/batched-bench.exe,sha256=_mvGjJDmgKPtFKyDBcqEjVpqWBbTIwL_s8EbAA_U-uE,206848
-bigdl/cpp/libs/batched.exe,sha256=5MrUppH2YaErh4dd65tM8hI9NFbZqmDiiZJAH6ltRHo,208896
-bigdl/cpp/libs/beam-search.exe,sha256=XbF_HUIJYP_ZK6D7iS3IxOnwQ0bqvKFJ6NUdB6_NRBM,214528
-bigdl/cpp/libs/benchmark.exe,sha256=XbGcY7-n8gs3SW74itSYT5I6U1UPZEQpzoN0WrdEIZY,74240
-bigdl/cpp/libs/common.lib,sha256=GxJVrina6Fhn3k5zTuyLoaIUbPGctPeL135wC7-6B_4,3330124
-bigdl/cpp/libs/convert-llama2c-to-ggml.exe,sha256=1MdEedCb87uR774fU-eu-Khs7Ev58726B4zEXJ_G24w,126464
-bigdl/cpp/libs/embedding.exe,sha256=drv2pmTn54IObOhLf73MnktJcb-fR7Qx7ui32thaI_w,644096
-bigdl/cpp/libs/export-lora.exe,sha256=wyhWIn-pbN65XnEJzitlRhXyn76ia2ehp9ZcyGXk9r0,90112
-bigdl/cpp/libs/finetune.exe,sha256=TFRojX1MNJpwlkbmqwsZCPNh2z5D36YrlVTG4trC-nc,302592
-bigdl/cpp/libs/ggml_shared.dll,sha256=SDvhXuJCektp3ojaMwYCGPVeD6X0ewEOctMtcqSCVbY,6305280
-bigdl/cpp/libs/gguf.exe,sha256=xFosICE0Jt4wfJno7XQKAZ7FubhWWFdZE3V-j3s6_as,5817856
-bigdl/cpp/libs/gritlm.exe,sha256=-hxhi65u3iaeyDxz7Fy3RFaJZ9gBdf8AFoyM6HQSzJg,638464
-bigdl/cpp/libs/imatrix.exe,sha256=rDFCEqDf3dwIiPFtajs21HgZdackbEWt9l1A_3REvaE,676352
-bigdl/cpp/libs/infill.exe,sha256=uBxrhbWqjA5VZbqQ3ac_0UQ_3HuTHswKBSVEfgwy_lk,733184
-bigdl/cpp/libs/llama-bench.exe,sha256=jz-Tyd85fwaQlTlTxf1pT02LLbZNOhlYSvWK7HgCiIU,336384
-bigdl/cpp/libs/llama.dll,sha256=dSYfIYzwimP9RuV1i5CuFff6jIlZgjO0uy1gBVVMhHA,7926272
-bigdl/cpp/libs/llava-cli.exe,sha256=DDx2Pa3sFZTnigpIpQqhGhR4YlYYctuPjlVmxbiAgZI,921600
-bigdl/cpp/libs/llava_shared.dll,sha256=-lBVZzl0Re4_ohjGVmi5gpwkhyKh99bHNNqXpgAkMk8,6572544
-bigdl/cpp/libs/lookahead.exe,sha256=Ld2Fnj0ECmbftDio1d0GT06dlt5_g2euzRDabJNUAOQ,684032
-bigdl/cpp/libs/lookup.exe,sha256=pwA7R8EttwnoZinMMgoAYk5IO2YKJeIRiSuzMjLpdeg,718336
-bigdl/cpp/libs/ls-sycl-device.exe,sha256=OOc6F6TJ-sSi6-jZ0G5E9A8frXJmgRdFbU9NDnPDiWk,10240
-bigdl/cpp/libs/main.exe,sha256=RDlZ7oV8lZUhl73Z-AqNscFlxI15XUB17Vwu0HtdesI,764416
-bigdl/cpp/libs/ollama.exe,sha256=sQKMKMv9wI05YQEu90BqJduQs1gCDTXJdpGvda9Gwek,64183875
-bigdl/cpp/libs/parallel.exe,sha256=tkLrbB7wLmK8zpCvanwOsWqzVD5JmjharMQtfwLvzTk,701440
-bigdl/cpp/libs/passkey.exe,sha256=f-dAB8g5DkJm67eS_migc3qtWL8752uHCLEH0AVDy14,216064
-bigdl/cpp/libs/perplexity.exe,sha256=Ucz5OBMRo_MTn2RQefpKmyO1g8FfPmbJv5rWrw3c81c,782336
-bigdl/cpp/libs/q8dot.exe,sha256=USHFPdZKMaW6pK-3UbbnspN5xh0w2Vx02uC2Hkvu4Qs,53760
-bigdl/cpp/libs/quantize-stats.exe,sha256=Hk2uJBdre5Dm0uoXXPZ_nuj-s0tumoDq_5DWLT7ObSY,130048
-bigdl/cpp/libs/quantize.exe,sha256=aLtFyIQujCmV6k-Kj7hBMfGfLynPNIIkFpPG8_lpOUM,235520
-bigdl/cpp/libs/save-load-state.exe,sha256=7wsKMC662N4Y9SdKT6lnb_E4DMSzT-POyCZ45fXGnVk,636416
-bigdl/cpp/libs/server.exe,sha256=b_bWcsqxedciHqq466RAtjZf_2cNBJ1dYzYzw1j9Nvk,1731584
-bigdl/cpp/libs/simple.exe,sha256=IDazWzUsdk7CdC0KYzROiBFnZ6ActnwMArBk8VHX2Rk,202752
-bigdl/cpp/libs/speculative.exe,sha256=9C0BmzyQrIWbxQh_qVYotbEab0tjY6K9B9gpsp7wdNU,709632
-bigdl/cpp/libs/tokenize.exe,sha256=uKiTcb8pSqz0jwhOUVUDKWGSDn-hAvU1vEYWQus23Y0,203264
-bigdl/cpp/libs/train-text-from-scratch.exe,sha256=1EW0FAd4vvA-vQlQS-oew6vTJSYLZY4J9XD_gV4Gd8g,283648
-bigdl/cpp/libs/vdot.exe,sha256=D2kks4z1iYFGjdy8el6yWvpjYP6KhTtW8rpY-cc5_cE,56320
-bigdl/cpp/libs/dist/windows-amd64/ollama_runners/cpu/ollama_llama_server.exe,sha256=F-w8mJEwDDo7IL6gdyJ4YzctFhH3X8CCn3zgJ2r9X98,8601600
-bigdl/cpp/libs/dist/windows-amd64/ollama_runners/cpu_avx/ollama_llama_server.exe,sha256=ngkBXScUtu-IDWhCq0AVbNOq16C1vFBRlfjnVBrKkVw,8601600
-bigdl/cpp/libs/dist/windows-amd64/ollama_runners/cpu_avx2/ollama_llama_server.exe,sha256=MzZRy3qMHCfaD9C0k7dISs8s--EwhLx-l6onJn6UkyY,8601600
-bigdl_core_cpp-2.5.0b20240728.data/scripts/init-llama-cpp.bat,sha256=13AgSYRyzk6hlSz11dPyCMJeSoW9z8PZ9l85E_5GWxs,528
-bigdl_core_cpp-2.5.0b20240728.data/scripts/init-llama-cpp.ps1,sha256=JFOylLxO4MKpllHhdbPuJ1xHi9azxDpzdJns8JtZpkU,501
-bigdl_core_cpp-2.5.0b20240728.data/scripts/init-ollama.bat,sha256=I2em4AnSSMq7LX3IRI3QR9w3UY2y2Y8zXQkpL09-G7w,472
-bigdl_core_cpp-2.5.0b20240728.dist-info/METADATA,sha256=_gOubzpQIztQjq9sMKLgwLg4-Dpb0wLuLV8KdI38Ndg,668
-bigdl_core_cpp-2.5.0b20240728.dist-info/WHEEL,sha256=at4xwl6JdXdkZHxdo5ixTwJ7ENtVftSy2wqmsdmo_4U,98
-bigdl_core_cpp-2.5.0b20240728.dist-info/top_level.txt,sha256=iGuLfZARD_qANcIMfy0tbbrC3EtCg6BSiH8icc3dLWs,6
-bigdl_core_cpp-2.5.0b20240728.dist-info/RECORD,,