Huggingface.js documentation
@huggingface/gguf
@huggingface/inference
使用 Inference ClientAPI 参考
类
HfInferenceInferenceClientInferenceClientEndpointInferenceClientErrorInferenceClientHubApiErrorInferenceClientInputErrorInferenceClientProviderApiErrorInferenceClientProviderOutputErrorInferenceClientRoutingError
接口
AudioToAudioOutputAudioToAudioOutputElemBaseArgsBodyParamsHeaderParamsInferenceProviderMappingEntryLogger选项TextGenerationInputTextGenerationOutputTextGenerationStreamBestOfSequenceTextGenerationStreamDetailsTextGenerationStreamOutputTextGenerationStreamPrefillTokenTextGenerationStreamTokenUrlParams
模块
@huggingface/hub
与 Hub 交互API 参考
类
接口
AuthInfoCachedFileInfoCachedRepoInfoCachedRevisionInfoCommitCopyFileCommitDataCommitDeletedEntryCommitEditFileCommitEditFileParamsCommitFileCommitInfoCommitOutputCopyDestinationCopyFilesEntryCopyProgressEventCopySource凭据DatasetEntryFileDownloadInfoOutputHFCacheInfoJobVolumeLfsPathInfoListFileEntryMlxQuantizationConfigModelConfigModelDerivedFieldsModelEntryOAuthResultParallelDownloadOptionsPathInfoQuantizationConfigRangeEditCacheEntryRepoIdSafetensorsIndexJsonSafetensorsShardFileInfoSecurityFileStatusSpaceEntrySpaceResourceConfigSpaceResourceRequirementSpaceRuntimeTensorInfoUserInfoWhoAmIAppWhoAmIOrgWhoAmIUserXetFileInfoXetReadToken
@huggingface/mcp-client
@huggingface/tiny-agents
@huggingface/space-header
@huggingface/gguf
@huggingface/lerobot
@huggingface/usd-web-viewer
@huggingface/gguf
一个适用于远程托管文件的 GGUF 解析器。
规范
规范:https://github.com/ggerganov/ggml/blob/master/docs/gguf.md
参考实现(Python):https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/gguf/gguf_reader.py
安装
npm install @huggingface/gguf
用法
基本用法
import { GGMLQuantizationType, gguf } from "@huggingface/gguf";
// remote GGUF file from https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF
const URL_LLAMA = "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/191239b/llama-2-7b-chat.Q2_K.gguf";
const { metadata, tensorInfos } = await gguf(URL_LLAMA);
console.log(metadata);
// {
// version: 2,
// tensor_count: 291n,
// kv_count: 19n,
// "general.architecture": "llama",
// "general.file_type": 10,
// "general.name": "LLaMA v2",
// ...
// }
console.log(tensorInfos);
// [
// {
// name: "token_embd.weight",
// shape: [4096n, 32000n],
// dtype: GGMLQuantizationType.Q2_K,
// },
// ... ,
// {
// name: "output_norm.weight",
// shape: [4096n],
// dtype: GGMLQuantizationType.F32,
// }
// ]
读取本地文件
// Reading a local file. (Not supported on browser)
const { metadata, tensorInfos } = await gguf(
'./my_model.gguf',
{ allowLocalFile: true },
);类型化元数据
通过设置 typedMetadata: true,您可以获取包含类型信息的元数据。这将同时提供原始值及其 GGUF 数据类型:
import { GGMLQuantizationType, GGUFValueType, gguf } from "@huggingface/gguf";
const URL_LLAMA = "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/191239b/llama-2-7b-chat.Q2_K.gguf";
const { metadata, typedMetadata } = await gguf(URL_LLAMA, { typedMetadata: true });
console.log(typedMetadata);
// {
// version: { value: 2, type: GGUFValueType.UINT32 },
// tensor_count: { value: 291n, type: GGUFValueType.UINT64 },
// kv_count: { value: 19n, type: GGUFValueType.UINT64 },
// "general.architecture": { value: "llama", type: GGUFValueType.STRING },
// "general.file_type": { value: 10, type: GGUFValueType.UINT32 },
// "general.name": { value: "LLaMA v2", type: GGUFValueType.STRING },
// "llama.attention.head_count": { value: 32, type: GGUFValueType.UINT32 },
// "llama.attention.layer_norm_rms_epsilon": { value: 9.999999974752427e-7, type: GGUFValueType.FLOAT32 },
// "tokenizer.ggml.tokens": { value: ["<unk>", "<s>", "</s>", ...], type: GGUFValueType.ARRAY, subType: GGUFValueType.STRING },
// "tokenizer.ggml.scores": { value: [0.0, -1000.0, -1000.0, ...], type: GGUFValueType.ARRAY, subType: GGUFValueType.FLOAT32 },
// ...
// }
// Access both value and type information
console.log(typedMetadata["general.architecture"].value); // "llama"
console.log(typedMetadata["general.architecture"].type); // GGUFValueType.STRING (8)
// For arrays, subType indicates the type of array elements
console.log(typedMetadata["tokenizer.ggml.tokens"].type); // GGUFValueType.ARRAY (9)
console.log(typedMetadata["tokenizer.ggml.tokens"].subType); // GGUFValueType.STRING (8)严格类型
默认情况下,metadata 中的已知字段具有类型。这包括在 llama.cpp、whisper.cpp 和 ggml 中发现的各种字段。
const { metadata, tensorInfos } = await gguf(URL_MODEL);
// Type check for model architecture at runtime
if (metadata["general.architecture"] === "llama") {
// "llama.attention.head_count" is a valid key for llama architecture, this is typed as a number
console.log(model["llama.attention.head_count"]);
// "mamba.ssm.conv_kernel" is an invalid key, because it requires model architecture to be mamba
console.log(model["mamba.ssm.conv_kernel"]); // error
}Disable strictly typed
由于 GGUF 格式可用于存储张量,因此从技术上讲,我们可以将其用于其他用途。例如,存储 控制向量、lora 权重等。
如果您想使用自己的 GGUF 元数据结构,可以通过将解析输出强制转换为 GGUFParseOutput<{ strict: false }> 来禁用严格类型检查:
const { metadata, tensorInfos }: GGUFParseOutput<{ strict: false }> = await gguf(URL_LLAMA);命令行界面
此包提供了与 gguf_dump.py 脚本等效的 CLI。您可以使用以下命令导出 GGUF 元数据和张量列表:
npx @huggingface/gguf my_model.gguf
# or, with a remote GGUF file:
# npx @huggingface/gguf https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf输出示例:
* Dumping 36 key/value pair(s)
Idx | Count | Value
----|--------|----------------------------------------------------------------------------------
1 | 1 | version = 3
2 | 1 | tensor_count = 292
3 | 1 | kv_count = 33
4 | 1 | general.architecture = "llama"
5 | 1 | general.type = "model"
6 | 1 | general.name = "Meta Llama 3.1 8B Instruct"
7 | 1 | general.finetune = "Instruct"
8 | 1 | general.basename = "Meta-Llama-3.1"
[truncated]
* Dumping 292 tensor(s)
Idx | Num Elements | Shape | Data Type | Name
----|--------------|--------------------------------|-----------|--------------------------
1 | 64 | 64, 1, 1, 1 | F32 | rope_freqs.weight
2 | 525336576 | 4096, 128256, 1, 1 | Q4_K | token_embd.weight
3 | 4096 | 4096, 1, 1, 1 | F32 | blk.0.attn_norm.weight
4 | 58720256 | 14336, 4096, 1, 1 | Q6_K | blk.0.ffn_down.weight
[truncated]或者,您可以将此包安装为全局包,这将提供 gguf-view 命令:
npm i -g @huggingface/gguf gguf-view my_model.gguf
Hugging Face Hub
Hub 支持所有文件格式,并内置了 GGUF 格式的功能。
更多信息请参见:http://hf.co/docs/hub/gguf。
致谢与灵感
- @platypii 的 https://github.com/hyparam/hyllama(MIT 许可证)
- @biw @dkogut1996 @spencekim 的 https://github.com/ahoylabs/gguf.js(MIT 许可证)
🔥❤️
Update on GitHub