返回模型

说明文档

Granite 3.0 2b instruct 启用键值缓存的 ONNX fp16 格式版本

模型创建者：IBM-Granite
原始模型：IBM-Granite Granite 3.0 2b instruct

描述

本仓库包含由 Esperanto Technologies 制作的 Granite 3.0 2b instruct ONNX 转换文件。该模型采用 fp16 格式，并启用了 KVC（键值缓存）。

如何下载 ONNX 模型和权重文件

获取模型最简单的方法是克隆整个仓库。或者，你也可以使用 huggingface-hub Python 库下载文件。

pip3 install huggingface-hub>=0.17.1

然后你可以使用如下命令将任意单个模型文件高速下载到当前目录：

huggingface-cli download Esperanto/granite-3.0-2b-instruct-kvc-fp16-onnx --local-dir granite-3.0-2b-instruct-kvc-fp16-onnx --local-dir-use-symlinks False

更多关于使用 huggingface-cli 下载的文档，请参阅：HF -> Hub Python Library -> Download files -> Download from the CLI。

如何使用 ONNXRuntime 从 Python 代码运行

该模型可以轻松在 CPU 上使用 ONNXRuntime 运行。

首先安装依赖包

pip3 install onnx==1.16.1
pip3 install onnxruntime==1.17.1

示例代码：使用此模型生成文本

我们使用贪婪解码定义循环：

import numpy as np
import onnxruntime
import onnx
from transformers import AutoTokenizer

def generate_text(model_path, prompt, tokenizer, max_gen_tokens, total_sequence, window, context):
    model = onnx.load(model_path)

    #我们为第一次迭代创建输入
    input_tensor = tokenizer(prompt, return_tensors=\"pt\")
    prompt_size = len(input_tensor['input_ids'][0])
    actual_input = input_tensor['input_ids']
    if prompt_size < window:
        actual_input = np.concatenate((tokenizer.bos_token_id*np.ones([1, window - prompt_size], dtype = 'int64'),
                                       actual_input), axis=1)
    if prompt_size + max_gen_tokens > total_sequence:
        print(\"错误：需要更长的总序列长度！\")
        return
    first_attention = np.concatenate((np.zeros([1, total_sequence - window], dtype = 'int64'),
                                      np.ones((1, window), dtype = 'int64')), axis=1)
    max_gen_tokens += prompt_size #我们需要在解析提示词的基础上进行生成
    inputs_names =[node.name for node in model.graph.input]
    output_names =[node.name for node in model.graph.output]
    n_heads = 8 #kvc的gqa头数
    inputs_dict = {}
    inputs_dict['input_ids'] = actual_input[:, :window].reshape(1, window).numpy()
    inputs_dict['attention_mask'] = first_attention
    index_pos = sum(first_attention[0])
    inputs_dict['position_ids'] = np.concatenate((np.zeros([1, total_sequence - index_pos], dtype = 'int64'), np.arange(index_pos, dtype = 'int64').reshape(1, index_pos)), axis=1)
    inputs_dict['tree_attention'] = np.triu(-65504*np.ones(total_sequence), k= 1).astype('float16').reshape(1, 1, total_sequence, total_sequence)
    for name in inputs_names:
        if name == 'input_ids' or name == 'attention_mask' or name == 'position_ids' or name == 'tree_attention': continue
        inputs_dict[name] = np.zeros([1, n_heads, context-window, 64], dtype=\"float16\")
    index = 0
    new_token = np.array([10])
    next_index = window
    old_j = 0
    total_input = actual_input.numpy()

    rt_session = onnxruntime.InferenceSession(model_path)
    ## 我们运行推理
    while next_index < max_gen_tokens:
        if new_token.any() == tokenizer.eos_token_id:
            break
        #推理
        output = rt_session.run(output_names, inputs_dict)
        outs_dictionary = {name: content for (name, content) in zip (output_names, output)}
        #我们为下一次推理准备输入
        for name in inputs_names:
            if name == 'input_ids':
                old_j = next_index
                if next_index < prompt_size:
                    if prompt_size - next_index >= window: next_index += window
                    else: next_index = prompt_size 
                    j = next_index - window
                else:
                    next_index +=1
                    j = next_index - window
                    new_token = outs_dictionary['logits'].argmax(-1).reshape(1, window)
                    total_input = np.concatenate((total_input, new_token[: , -1:]), axis = 1)
                inputs_dict['input_ids']= total_input[:, j:next_index].reshape(1, window)
            elif name == 'attention_mask':
                inputs_dict['attention_mask'] = np.concatenate((np.zeros((1, total_sequence-next_index), dtype = 'int64'), np.ones((1, next_index), dtype = 'int64')), axis=1)
            elif name == 'position_ids':
                inputs_dict['position_ids'] = np.concatenate((np.zeros([1, total_sequence - next_index], dtype = 'int64'), np.arange(next_index, dtype = 'int64').reshape(1, next_index)), axis=1)
            elif name == 'tree_attention': continue
            else:
                old_name = name.replace(\"past_key_values\", \"present\")
                inputs_dict[name] = outs_dictionary[old_name][:, :, next_index-old_j:context-window+(next_index - old_j), :]

    answer = tokenizer.decode(total_input[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
    return answer

现在我们运行推理：

tokenizer = AutoTokenizer.from_pretrained(\"Esperanto/granite-3.0-2b-instruct-kvc-fp16-onnx\")
model_path = \"granite-3.0-2b-instruct-kvc-fp16-onnx/model.onnx\"

max_gen_tokens = 20    #我们想要生成的token数量
total_sequence = 128   #总序列长度
context = 1024         #扩展kvc的上下文长度
window = 16            #每次想要解析的token数量
messages = [
    {\"role\": \"system\", \"content\": \"You are a pirate chatbot who always responds in pirate speak!\"},
    {\"role\": \"user\", \"content\": \"Who are you?\"},
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

generated = generate_text(model_path, prompt, tokenizer, max_gen_tokens, total_sequence, window, context)
print(generated)

Esperanto/granite-3.0-2b-instruct-kvc-fp16-onnx

作者 Esperanto

text-generation transformers

↓ 0 ♥ 0

创建时间: 2024-10-24 15:00:54+00:00

更新时间: 2025-02-04 10:01:16+00:00

在 Hugging Face 上查看

文件 (372)

.gitattributes

README.md

added_tokens.json

config.json

merges.txt

model.embed_tokens.weight

model.layers.0.input_layernorm.weight

model.layers.0.post_attention_layernorm.weight

model.layers.1.input_layernorm.weight

model.layers.1.post_attention_layernorm.weight

model.layers.10.input_layernorm.weight

model.layers.10.post_attention_layernorm.weight

model.layers.11.input_layernorm.weight

model.layers.11.post_attention_layernorm.weight

model.layers.12.input_layernorm.weight

model.layers.12.post_attention_layernorm.weight

model.layers.13.input_layernorm.weight

model.layers.13.post_attention_layernorm.weight

model.layers.14.input_layernorm.weight

model.layers.14.post_attention_layernorm.weight

model.layers.15.input_layernorm.weight

model.layers.15.post_attention_layernorm.weight

model.layers.16.input_layernorm.weight

model.layers.16.post_attention_layernorm.weight

model.layers.17.input_layernorm.weight

model.layers.17.post_attention_layernorm.weight

model.layers.18.input_layernorm.weight

model.layers.18.post_attention_layernorm.weight

model.layers.19.input_layernorm.weight

model.layers.19.post_attention_layernorm.weight

model.layers.2.input_layernorm.weight

model.layers.2.post_attention_layernorm.weight

model.layers.20.input_layernorm.weight

model.layers.20.post_attention_layernorm.weight

model.layers.21.input_layernorm.weight

model.layers.21.post_attention_layernorm.weight

model.layers.22.input_layernorm.weight

model.layers.22.post_attention_layernorm.weight

model.layers.23.input_layernorm.weight

model.layers.23.post_attention_layernorm.weight

model.layers.24.input_layernorm.weight

model.layers.24.post_attention_layernorm.weight

model.layers.25.input_layernorm.weight

model.layers.25.post_attention_layernorm.weight

model.layers.26.input_layernorm.weight

model.layers.26.post_attention_layernorm.weight

model.layers.27.input_layernorm.weight

model.layers.27.post_attention_layernorm.weight

model.layers.28.input_layernorm.weight

model.layers.28.post_attention_layernorm.weight

model.layers.29.input_layernorm.weight

model.layers.29.post_attention_layernorm.weight

model.layers.3.input_layernorm.weight

model.layers.3.post_attention_layernorm.weight

model.layers.30.input_layernorm.weight

model.layers.30.post_attention_layernorm.weight

model.layers.31.input_layernorm.weight

model.layers.31.post_attention_layernorm.weight

model.layers.32.input_layernorm.weight

model.layers.32.post_attention_layernorm.weight

model.layers.33.input_layernorm.weight

model.layers.33.post_attention_layernorm.weight

model.layers.34.input_layernorm.weight

model.layers.34.post_attention_layernorm.weight

model.layers.35.input_layernorm.weight

model.layers.35.post_attention_layernorm.weight

model.layers.36.input_layernorm.weight

model.layers.36.post_attention_layernorm.weight

model.layers.37.input_layernorm.weight

model.layers.37.post_attention_layernorm.weight

model.layers.38.input_layernorm.weight

model.layers.38.post_attention_layernorm.weight

model.layers.39.input_layernorm.weight

model.layers.39.post_attention_layernorm.weight

model.layers.4.input_layernorm.weight

model.layers.4.post_attention_layernorm.weight

model.layers.5.input_layernorm.weight

model.layers.5.post_attention_layernorm.weight

model.layers.6.input_layernorm.weight

model.layers.6.post_attention_layernorm.weight

model.layers.7.input_layernorm.weight

model.layers.7.post_attention_layernorm.weight

model.layers.8.input_layernorm.weight

model.layers.8.post_attention_layernorm.weight

model.layers.9.input_layernorm.weight

model.layers.9.post_attention_layernorm.weight

model.norm.weight

model.onnx ONNX

onnx__MatMul_11599

onnx__MatMul_11600

onnx__MatMul_11601

onnx__MatMul_11630

onnx__MatMul_11631

onnx__MatMul_11632

onnx__MatMul_11633

onnx__MatMul_11634

onnx__MatMul_11635

onnx__MatMul_11636

onnx__MatMul_11665

onnx__MatMul_11666

onnx__MatMul_11667

onnx__MatMul_11668

onnx__MatMul_11669

onnx__MatMul_11670

onnx__MatMul_11671

onnx__MatMul_11700

onnx__MatMul_11701

onnx__MatMul_11702

onnx__MatMul_11703

onnx__MatMul_11704

onnx__MatMul_11705

onnx__MatMul_11706

onnx__MatMul_11735

onnx__MatMul_11736

onnx__MatMul_11737

onnx__MatMul_11738

onnx__MatMul_11739

onnx__MatMul_11740

onnx__MatMul_11741

onnx__MatMul_11770

onnx__MatMul_11771

onnx__MatMul_11772

onnx__MatMul_11773

onnx__MatMul_11774

onnx__MatMul_11775

onnx__MatMul_11776

onnx__MatMul_11805

onnx__MatMul_11806

onnx__MatMul_11807

onnx__MatMul_11808

onnx__MatMul_11809

onnx__MatMul_11810

onnx__MatMul_11811

onnx__MatMul_11840

onnx__MatMul_11841

onnx__MatMul_11842

onnx__MatMul_11843

onnx__MatMul_11844

onnx__MatMul_11845

onnx__MatMul_11846

onnx__MatMul_11875

onnx__MatMul_11876

onnx__MatMul_11877

onnx__MatMul_11878

onnx__MatMul_11879

onnx__MatMul_11880

onnx__MatMul_11881

onnx__MatMul_11910

onnx__MatMul_11911

onnx__MatMul_11912

onnx__MatMul_11913

onnx__MatMul_11914

onnx__MatMul_11915

onnx__MatMul_11916

onnx__MatMul_11945

onnx__MatMul_11946

onnx__MatMul_11947

onnx__MatMul_11948

onnx__MatMul_11949

onnx__MatMul_11950

onnx__MatMul_11951

onnx__MatMul_11980

onnx__MatMul_11981

onnx__MatMul_11982

onnx__MatMul_11983

onnx__MatMul_11984

onnx__MatMul_11985

onnx__MatMul_11986

onnx__MatMul_12015

onnx__MatMul_12016

onnx__MatMul_12017

onnx__MatMul_12018

onnx__MatMul_12019

onnx__MatMul_12020

onnx__MatMul_12021

onnx__MatMul_12050

onnx__MatMul_12051

onnx__MatMul_12052

onnx__MatMul_12053

onnx__MatMul_12054

onnx__MatMul_12055

onnx__MatMul_12056

onnx__MatMul_12085

onnx__MatMul_12086

onnx__MatMul_12087

onnx__MatMul_12088

onnx__MatMul_12089

onnx__MatMul_12090

onnx__MatMul_12091

onnx__MatMul_12120

onnx__MatMul_12121

onnx__MatMul_12122

onnx__MatMul_12123

onnx__MatMul_12124

onnx__MatMul_12125

onnx__MatMul_12126

onnx__MatMul_12155

onnx__MatMul_12156

onnx__MatMul_12157

onnx__MatMul_12158

onnx__MatMul_12159

onnx__MatMul_12160

onnx__MatMul_12161

onnx__MatMul_12190

onnx__MatMul_12191

onnx__MatMul_12192

onnx__MatMul_12193

onnx__MatMul_12194

onnx__MatMul_12195

onnx__MatMul_12196

onnx__MatMul_12225

onnx__MatMul_12226

onnx__MatMul_12227

onnx__MatMul_12228

onnx__MatMul_12229

onnx__MatMul_12230

onnx__MatMul_12231

onnx__MatMul_12260

onnx__MatMul_12261

onnx__MatMul_12262

onnx__MatMul_12263

onnx__MatMul_12264

onnx__MatMul_12265

onnx__MatMul_12266

onnx__MatMul_12295

onnx__MatMul_12296

onnx__MatMul_12297

onnx__MatMul_12298

onnx__MatMul_12299

onnx__MatMul_12300

onnx__MatMul_12301

onnx__MatMul_12330

onnx__MatMul_12331

onnx__MatMul_12332

onnx__MatMul_12333

onnx__MatMul_12334

onnx__MatMul_12335

onnx__MatMul_12336

onnx__MatMul_12365

onnx__MatMul_12366

onnx__MatMul_12367

onnx__MatMul_12368

onnx__MatMul_12369

onnx__MatMul_12370

onnx__MatMul_12371

onnx__MatMul_12400

onnx__MatMul_12401

onnx__MatMul_12402

onnx__MatMul_12403

onnx__MatMul_12404

onnx__MatMul_12405

onnx__MatMul_12406

onnx__MatMul_12435

onnx__MatMul_12436

onnx__MatMul_12437

onnx__MatMul_12438

onnx__MatMul_12439

onnx__MatMul_12440

onnx__MatMul_12441

onnx__MatMul_12470

onnx__MatMul_12471

onnx__MatMul_12472

onnx__MatMul_12473

onnx__MatMul_12474

onnx__MatMul_12475

onnx__MatMul_12476

onnx__MatMul_12505

onnx__MatMul_12506

onnx__MatMul_12507

onnx__MatMul_12508

onnx__MatMul_12509

onnx__MatMul_12510

onnx__MatMul_12511

onnx__MatMul_12540

onnx__MatMul_12541

onnx__MatMul_12542

onnx__MatMul_12543

onnx__MatMul_12544

onnx__MatMul_12545

onnx__MatMul_12546

onnx__MatMul_12575

onnx__MatMul_12576

onnx__MatMul_12577

onnx__MatMul_12578

onnx__MatMul_12579

onnx__MatMul_12580

onnx__MatMul_12581

onnx__MatMul_12610

onnx__MatMul_12611

onnx__MatMul_12612

onnx__MatMul_12613

onnx__MatMul_12614

onnx__MatMul_12615

onnx__MatMul_12616

onnx__MatMul_12645

onnx__MatMul_12646

onnx__MatMul_12647

onnx__MatMul_12648

onnx__MatMul_12649

onnx__MatMul_12650

onnx__MatMul_12651

onnx__MatMul_12680

onnx__MatMul_12681

onnx__MatMul_12682

onnx__MatMul_12683

onnx__MatMul_12684

onnx__MatMul_12685

onnx__MatMul_12686

onnx__MatMul_12715

onnx__MatMul_12716

onnx__MatMul_12717

onnx__MatMul_12718

onnx__MatMul_12719

onnx__MatMul_12720

onnx__MatMul_12721

onnx__MatMul_12750

onnx__MatMul_12751

onnx__MatMul_12752

onnx__MatMul_12753

onnx__MatMul_12754

onnx__MatMul_12755

onnx__MatMul_12756

onnx__MatMul_12785

onnx__MatMul_12786

onnx__MatMul_12787

onnx__MatMul_12788

onnx__MatMul_12789

onnx__MatMul_12790

onnx__MatMul_12791

onnx__MatMul_12820

onnx__MatMul_12821

onnx__MatMul_12822

onnx__MatMul_12823

onnx__MatMul_12824

onnx__MatMul_12825

onnx__MatMul_12826

onnx__MatMul_12855

onnx__MatMul_12856

onnx__MatMul_12857

onnx__MatMul_12858

onnx__MatMul_12859

onnx__MatMul_12860

onnx__MatMul_12861

onnx__MatMul_12890

onnx__MatMul_12891

onnx__MatMul_12892

onnx__MatMul_12893

onnx__MatMul_12894

onnx__MatMul_12895

onnx__MatMul_12896

onnx__MatMul_12925

onnx__MatMul_12926

onnx__MatMul_12927

onnx__MatMul_12928

onnx__MatMul_12929

onnx__MatMul_12930

onnx__MatMul_12931

onnx__MatMul_12960

onnx__MatMul_12961

onnx__MatMul_12962

onnx__MatMul_12963

onnx__MatMul_12964

onnx__MatMul_12965

onnx__MatMul_12966

onnx__MatMul_12995

onnx__MatMul_12996

onnx__MatMul_12997

onnx__MatMul_12998

special_tokens_map.json

tokenizer.json

tokenizer_config.json

vocab.json