Hugging Face pipeline¶

Snowflake Model Registry 支持任何指定为转换器 (link removed) 且可使用 transformers.Pipeline (link removed) 方法加载的 Hugging Face 模型。

使用以下方法之一将 Hugging Face 模型记录到 Model Registry：

使用 Snowsight 从 Hugging Face 导入和部署模型。有关说明，请参阅 Import and deploy models from an external service。
创建 snowflake.ml.model.models.huggingface.TransformersPipeline 实例并调用 log_model()：
```
# reg: snowflake.ml.registry.Registry

from snowflake.ml.model.models import huggingface


model = huggingface.TransformersPipeline(
    task="text-classification",
    model="ProsusAI/finbert",
    # compute_pool_for_log=... # Optional
)

mv = reg.log_model(model, model_name='finbert', version_name='v5')
```
重要
- 如果未指定 compute_pool_for_log 实参，则使用默认的 CPU 计算池记录模型。
- 如果指定了 compute_pool_for_log 实参，则使用指定的计算池记录模型。
- 如果将 compute_pool_for_log 实参指定为 None，则模型文件会先下载到本地，然后上传到 Model Registry。这需要安装 huggingface-hub (https://pypi.org/project/huggingface-hub/)。

从内存中的 Hugging Face 加载模型并将其记录到 Model Registry：

# reg: snowflake.ml.registry.Registry

lm_hf_model = transformers.pipeline(
    task="text-generation",
    model="bigscience/bloom-560m",
    token="...",  # Put your HuggingFace token here.
    return_full_text=False,
    max_new_tokens=100,
)

lmv = reg.log_model(lm_hf_model, model_name='bloom', version_name='v560m')

如果您使用的是 Snowflake 笔记本，则为了下载模型的权重，您需要将外部访问集成附加到您的笔记本。要允许访问以下主机，需要此集成：

huggingface.co
hub-ci.huggingface.co
cdn-lfs-us-1.hf.co
cdn-lfs-eu-1.hf.co
cdn-lfs.hf.co
transfer.xethub.hf.co
cas-server.xethub.hf.co
cas-bridge.xethub.hf.c

备注

此主机列表仅包含访问 Hugging Face 所需的主机，且可能随时变更。您的模型可能需要来自其他来源的工件，应将这些工件添加到允许访问的网络规则中。

以下示例创建了一个新的外部访问集成 huggingface_network_rule，用于与笔记本一起使用：

CREATE NETWORK RULE huggingface_network_rule
TYPE = HOST_PORT
VALUE_LIST = (
    'huggingface.co',
    'hub-ci.huggingface.co',
    'cdn-lfs-us-1.hf.co',
    'cdn-lfs-eu-1.hf.co',
    'cdn-lfs.hf.co',
    'transfer.xethub.hf.co',
    'cas-server.xethub.hf.co',
    'cas-bridge.xethub.hf.co'
)
MODE = EGRESS
COMMENT = 'Network Rule for Hugging Face external access';

CREATE EXTERNAL ACCESS INTEGRATION huggingface_access_integration
ALLOWED_NETWORK_RULES = (huggingface_network_rule)
ENABLED = true;

有关更多信息，请参阅创建和使用外部访问集成。

创建外部访问集成后，将其附加到您的笔记本，即可有权访问 Hugging Face 模型存储库，以下载模型的权重和配置。有关更多信息，请参阅为 Snowflake Notebooks 设置外部访问。

模型注册表 API¶

调用 log_model() 时，options 字典支持以下键：


选项键	描述	类型
`target_methods`	模型对象上可用的方法列表。Hugging Face 模型默认使用对象的 `__call__` 方法（如果存在）。	`list[str]`
`cuda_version`	部署到具有 GPU 的平台时使用的 CUDA 运行时版本。如果设置为 `None`，该模型无法部署到具有 GPU 的平台。默认为 `12.4`。	`Optional[str]`

如果管道包含以下列表中的一个任务，模型注册表就会推断 signatures 实参：

fill-mask
question-answering（单个输出、多个输出）
summarization
table-question-answering
text2text-generation
text-classification（单个输出、多个输出）
sentiment-analysis（单个输出、多个输出）
text-generation）
token-classification
ner
translation
translation_xx_to_yy，其中 xx 和 yy 是 ISO 3166-1 alpha-2 (link removed) 中定义的双字母国家/地区代码
zero-shot-classification

备注

任务名称区分大小写。

Hugging Face 模型会忽略 sample_input_data 的 log_model 实参。在记录不在上述列表中的 Hugging Face 模型时指定 signatures 实参，以便注册表了解目标方法的签名。

要查看推断的签名，请调用 show_functions() 方法。此签名为您提供模型函数输入所需的类型和列名称及其输出格式。以下示例显示具有 text-generation 任务的模型 bigscience/bloom-560m 的签名：

{'name': '__CALL__',
  'target_method': '__call__',
  'signature': ModelSignature(
                      inputs=[
                          FeatureSpec(dtype=DataType.STRING, name='inputs')
                      ],
                      outputs=[
                          FeatureSpec(dtype=DataType.STRING, name='outputs')
                      ]
                  )}]

以下示例演示如何使用前面的签名调用模型：

# model: snowflake.ml.model.ModelVersion

import pandas as pd

remote_prediction = model.run(pd.DataFrame(["Hello, how are you?"], columns=["inputs"]))

使用说明¶

许多 Hugging Face 模型都很庞大，不适合标准仓库。请使用 Snowpark 优化型仓库，或者选择较小版本的模型。例如，Llama-2-70b-chat-hf 模型的替代项是 Llama-2-7b-chat-hf。
Snowflake 仓库没有 GPUs。仅使用 CPU 优化型 Hugging Face 模型。
有些 Hugging Face 转换器会为每个输入行返回一个字典数组。模型注册表会将字典数组转换为包含数组的 JSON 表示的字符串。例如，多重输出问题回答输出如下所示：
```
'[{"score": 0.61094731092453, "start": 139, "end": 178, "answer": "learn more about the world of athletics"},
{"score": 0.17750297486782074, "start": 139, "end": 180, "answer": "learn more about the world of athletics.\""}]'
```

示例¶

# Prepare model

import transformers
import pandas as pd

finbert_model = transformers.pipeline(
    task="text-classification",
    model="ProsusAI/finbert",
    top_k=2,
)

# Log the model
mv = registry.log_model(
    finbert_model,
    model_name="finbert",
    version_name="v1",
)

# Use the model
mv.run(pd.DataFrame(
        [
            ["I have a problem with my Snowflake that needs to be resolved asap!!", ""],
            ["I would like to have udon for today's dinner.", ""],
        ]
    )
)

结果：

0  [{"label": "negative", "score": 0.8106237053871155}, {"label": "neutral", "score": 0.16587384045124054}]
1  [{"label": "neutral", "score": 0.9263970851898193}, {"label": "positive", "score": 0.05286872014403343}]

Hugging Face 管道的推断签名¶

本部分介绍支持的 Hugging Face 管道的推断签名，包括所需输入和预期输出的描述和示例。所有输入和输出均为 Snowpark DataFrames。

Fill-mask 管道¶

“Fill-mask (link removed)”任务的管道具有以下输入和输出。

输入¶

inputs：要填充掩码的字符串。

示例：

--------------------------------------------------
|"inputs"                                        |
--------------------------------------------------
|LynYuu is the [MASK] of the Grand Duchy of Yu.  |
--------------------------------------------------

输出¶

outputs：一个字符串，包含以 JSON 格式表示的对象列表，列表中的每个对象都可能包含 score、token、token_str 或 sequence 等键。有关详细信息，请参阅 FillMaskPipeline (link removed)。

示例：

----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|"outputs"                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|[{"score": 0.9066258072853088, "token": 3007, "token_str": "capital", "sequence": "lynyuu is the capital of the grand duchy of yu."}, {"score": 0.08162177354097366, "token": 2835, "token_str": "seat", "sequence": "lynyuu is the seat of the grand duchy of yu."}, {"score": 0.0012052370002493262, "token": 4075, "token_str": "headquarters", "sequence": "lynyuu is the headquarters of the grand duchy of yu."}, {"score": 0.0006560495239682496, "token": 2171, "token_str": "name", "sequence": "lynyuu is the name of the grand duchy of yu."}, {"score": 0.0005427763098850846, "token": 3200, "token_str"...  |
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

代码示例¶
import transformers
import pandas as pd

model = transformers.pipeline(
    task="fill-mask",
    model="google-bert/bert-base-uncased",
)

mv = registry.log_model(
    model=model,
    model_name="GOOGLE_BERT_BASE_UNCASED",
)

input_df = pd.DataFrame([{"text": "LynYuu is the [MASK] of the Grand Duchy of Yu."}])
mv.run(
    input_df,
    # function_name="__call__", # Optional
)

令牌分类¶

“ner”或 token-classification (link removed) 任务的管道具有以下输入和输出。

输入¶

inputs：包含要分类的令牌的字符串。

示例：

------------------------------------------------
|"inputs"                                      |
------------------------------------------------
|My name is Izumi and I live in Tokyo, Japan.  |
------------------------------------------------

输出¶

outputs：一个字符串，包含以 JSON 格式表示的结果对象的列表，列表中的每个对象都可能包含 entity、score、index、word、name、start 或 end 等键。有关详细信息，请参阅 TokenClassificationPipeline <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.TokenClassificationPipeline (link removed)>`_。

示例：

----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|"outputs"                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|[{"entity": "PRON", "score": 0.9994392991065979, "index": 1, "word": "my", "start": 0, "end": 2}, {"entity": "NOUN", "score": 0.9968984127044678, "index": 2, "word": "name", "start": 3, "end": 7}, {"entity": "AUX", "score": 0.9937735199928284, "index": 3, "word": "is", "start": 8, "end": 10}, {"entity": "PROPN", "score": 0.9928083419799805, "index": 4, "word": "i", "start": 11, "end": 12}, {"entity": "PROPN", "score": 0.997334361076355, "index": 5, "word": "##zumi", "start": 12, "end": 16}, {"entity": "CCONJ", "score": 0.999173104763031, "index": 6, "word": "and", "start": 17, "end": 20}, {...  |

代码示例¶

import transformers
import pandas as pd

model = transformers.pipeline(
    task="token-classification",
    model="dslim/bert-base-NER",
)

mv = registry.log_model(
    model=model,
    model_name="BERT_BASE_NER",
)

mv.run(
    pd.DataFrame([{"inputs": "My name is Izumi and I live in Tokyo, Japan."}]),
    # function_name="__call__", # Optional
)

问答（单个输出）¶

“` question-answering <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.QuestionAnsweringPipeline (link removed)>`_”任务的管道，其中 top_k 未设置或设置为 1，具有以下输入和输出。

输入¶

question：包含要回答的问题的字符串。
context：可能包含答案的字符串。

示例：

-----------------------------------------------------------------------------------
|"question"                  |"context"                                           |
-----------------------------------------------------------------------------------
|What did Doris want to do?  |Doris is a cheerful mermaid from the ocean dept...  |
-----------------------------------------------------------------------------------

输出¶

score：浮点置信度分数从 0.0 到 1.0。
start：在上下文中，答案第一个词元的整数索引。
end：在原始上下文中，答案最后一个词元的整数索引。
answer：包含找到的答案的字符串。

示例：

--------------------------------------------------------------------------------
|"score"           |"start"  |"end"  |"answer"                                 |
--------------------------------------------------------------------------------
|0.61094731092453  |139      |178    |learn more about the world of athletics  |
--------------------------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd


model = transformers.pipeline(
    task="question-answering",
    model="deepset/roberta-base-squad2",
)

QA_input = {
    "question": "Why is model conversion important?",
    "context": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.",
}

mv = registry.log_model(
    model=model,
    model_name="ROBERTA_BASE_SQUAD2",
)

mv.run(
    pd.DataFrame.from_records([QA_input]),
    # function_name="__call__", # Optional
)

问答（多个输出）¶

任务是“` question-answering <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.QuestionAnsweringPipeline (link removed)>`_”的管道，其中 top_k 设置为大于 1，具有以下输入和输出。

输入¶

question：包含要回答的问题的字符串。
context：可能包含答案的字符串。

示例：

-----------------------------------------------------------------------------------
|"question"                  |"context"                                           |
-----------------------------------------------------------------------------------
|What did Doris want to do?  |Doris is a cheerful mermaid from the ocean dept...  |
-----------------------------------------------------------------------------------

输出¶

outputs：一个字符串，包含以 JSON 格式表示的结果对象的列表，列表中的每个对象都可能包含 score、start、end 或 answer 等键。

示例：

---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|"outputs"                                                                                                                                                                                                                                                                                                                                        |
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|[{"score": 0.61094731092453, "start": 139, "end": 178, "answer": "learn more about the world of athletics"}, {"score": 0.17750297486782074, "start": 139, "end": 180, "answer": "learn more about the world of athletics.\""}, {"score": 0.06438097357749939, "start": 138, "end": 178, "answer": "\"learn more about the world of athletics"}]  |
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd


model = transformers.pipeline(
    task="question-answering",
    model="deepset/roberta-base-squad2",
    top_k=3,
)

QA_input = {
    "question": "Why is model conversion important?",
    "context": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.",
}

mv = registry.log_model(
    model=model,
    model_name="ROBERTA_BASE_SQUAD2",
)

mv.run(
    pd.DataFrame.from_records([QA_input]),
    # function_name="__call__", # Optional
)

摘要¶

任务是“` summarization <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.SummarizationPipeline (link removed)>`_”的管道，其中 return_tensors 为 False 或未设置，具有以下输入和输出。

输入¶

documents：包含要汇总的文本的字符串。

示例：

------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|"documents"                                                                                                                                                                                               |
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|Neuro-sama is a chatbot styled after a female VTuber that hosts live streams on the Twitch channel "vedal987". Her speech and personality are generated by an artificial intelligence (AI) system  wh...  |
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

输出¶

summary_text：包含生成的摘要的字符串，或者，如果 num_return_sequences 大于 1，则字符串包含以 JSON 格式表示的结果列表，每个结果都是一个包含字段的字典，其中包括 summary_text。

示例：

---------------------------------------------------------------------------------
|"summary_text"                                                                 |
---------------------------------------------------------------------------------
| Neuro-sama is a chatbot styled after a female VTuber that hosts live streams  |
---------------------------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd


model = transformers.pipeline(
    task="summarization",
    model="facebook/bart-large-cnn",
)

text = "The transformers library is a great library for natural language processing which provides a unified interface for many different models and tasks."

mv = registry.log_model(
    model=model,
    model_name="BART_LARGE_CNN",
)

mv.run(
    pd.DataFrame.from_records([{"documents": text}]),
    # function_name="__call__", # Optional
)

表问答¶

任务是“` table-question-answering <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.TableQuestionAnsweringPipeline (link removed)>`_”的管道具有以下输入和输出。

输入¶

query：包含要回答的问题的字符串。
table：包含 JSON 序列化字典的字符串，形式为 {column -> [values]}，表示可能包含答案的表。

示例：

------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|"query"                                  |"table"                                                                                                                                                                                                                                                   |
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|Which channel has the most subscribers?  |{"Channel": ["A.I.Channel", "Kaguya Luna", "Mirai Akari", "Siro"], "Subscribers": ["3,020,000", "872,000", "694,000", "660,000"], "Videos": ["1,200", "113", "639", "1,300"], "Created At": ["Jun 30 2016", "Dec 4 2017", "Feb 28 2014", "Jun 23 2017"]}  |
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

输出¶

answer：包含可能答案的字符串。
coordinates：表示答案所在的单元格坐标的整数列表。
cells：包含答案所在的单元格内容的字符串列表。
aggregator：包含所用聚合器名称的字符串。

示例：

----------------------------------------------------------------
|"answer"     |"coordinates"  |"cells"          |"aggregator"  |
----------------------------------------------------------------
|A.I.Channel  |[              |[                |NONE          |
|             |  [            |  "A.I.Channel"  |              |
|             |    0,         |]                |              |
|             |    0          |                 |              |
|             |  ]            |                 |              |
|             |]              |                 |              |
----------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd
import json

model = transformers.pipeline(
    task="table-question-answering",
    model="microsoft/tapex-base-finetuned-wikisql",
)

data = {
    "year": [1896, 1900, 1904, 2004, 2008, 2012],
    "city": ["athens", "paris", "st. louis", "athens", "beijing", "london"],
}
query = "What is the city of the year 2004?"


mv = registry.log_model(
    model=model,
    model_name="TAPEX_BASE_FINETUNED_WIKISQL",
)

mv.run(
    pd.DataFrame.from_records([{"query": query, "table": json.dumps(data)}]),
    # function_name="__call__", # Optional
)

文本分类（单个输出）¶

“text-clasification (link removed)”任务的管道，其中 top_k 未设置或为 None，具有以下输入和输出。

输入¶

text：要分类的字符串。
text_pair：与 text 一起分类的字符串，用于计算文本相似度的模型。如果模型不使用它，则留空。

示例：

----------------------------------
|"text"       |"text_pair"       |
----------------------------------
|I like you.  |I love you, too.  |
----------------------------------

输出¶

label：表示文本分类标签的字符串。
score：浮点置信度分数从 0.0 到 1.0。

示例：

--------------------------------
|"label"  |"score"             |
--------------------------------
|LABEL_0  |0.9760091304779053  |
--------------------------------

代码示例¶

import transformers
import pandas as pd

model = transformers.pipeline(
    task="text-classification",
    model="cardiffnlp/twitter-roberta-base-sentiment-latest",
)

text = "I'm happy today!"


mv = registry.log_model(
    model=model,
    model_name="TWITTER_ROBERTA_BASE_SENTIMENT_LATEST",
)

mv.run(
    pd.DataFrame.from_records([{"text": text}]),
    # function_name="__call__", # Optional
)

文本分类（多个输出）¶

“text-clasification (link removed)”任务的管道，其中 top_k 设置为一个数字，具有以下输入和输出。

备注

如果将 top_k 设置为任何数字，即使该数字为 1，文本分类任务也被视为多个输出。要获取单个输出，请将 top_k 值设为 None。

输入¶

text：要分类的字符串。
text_pair：与 text 一起分类的字符串，用于计算文本相似度的模型。如果模型不使用它，则留空。

示例：

--------------------------------------------------------------------
|"text"                                              |"text_pair"  |
--------------------------------------------------------------------
|I am wondering if I should have udon or rice fo...  |             |
--------------------------------------------------------------------

输出¶

outputs：一个字符串，包含以 JSON 格式表示的结果列表，每个结果都包含包括 label 和 score 的字段。

示例：

--------------------------------------------------------
|"outputs"                                             |
--------------------------------------------------------
|[{"label": "NEGATIVE", "score": 0.9987024068832397}]  |
--------------------------------------------------------

代码示例¶

import transformers
import pandas as pd

model = transformers.pipeline(
    task="text-classification",
    model="cardiffnlp/twitter-roberta-base-sentiment-latest",
    top_k=3,
)

text = "I'm happy today!"


mv = registry.log_model(
    model=model,
    model_name="TWITTER_ROBERTA_BASE_SENTIMENT_LATEST",
)

mv.run(
    pd.DataFrame.from_records([{"text": text}]),
    # function_name="__call__", # Optional
)

文本到文本的生成¶

任务是“` text2text-generation <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.Text2TextGenerationPipeline (link removed)>`_”的管道，其中 return_tensors 为 False 或未设置，具有以下输入和输出。

输入¶

inputs：包含提示的字符串。

示例：

--------------------------------------------------------------------------------
|"inputs"                                                                      |
--------------------------------------------------------------------------------
|A descendant of the Lost City of Atlantis, who swam to Earth while saying, "  |
--------------------------------------------------------------------------------

输出¶

generated_text：如果 num_return_sequences 为 1，则为包含生成文本的字符串；如果 num_return_sequences 大于 1，则为以 JSON 格式表示字典结果列表的字符串，字典包含 generated_text 在内的字段。

示例：

----------------------------------------------------------------
|"generated_text"                                              |
----------------------------------------------------------------
|, said that he was a descendant of the Lost City of Atlantis  |
----------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd

model = transformers.pipeline(
    task="text2text-generation",
    model="google-t5/t5-small",
)

text = "Tell me a joke."


mv = registry.log_model(
    model=model,
    model_name="T5_SMALL",
)

mv.run(
    pd.DataFrame.from_records([{"inputs": text}]),
    # function_name="__call__", # Optional
)

备注

文本到文本的生成管道，其中 return_tensors 是 True，不受支持。

翻译生成¶

任务是“` translation <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.TranslationPipeline (link removed)>`_”的管道，其中 return_tensors 为 False 或未设置，具有以下输入和输出。

备注

翻译生成管道，其中 return_tensors 是 True，不受支持。

输入¶

inputs：包含要翻译的文本的字符串。

示例：

------------------------------------------------------------------------------------------------------
|"inputs"                                                                                            |
------------------------------------------------------------------------------------------------------
|Snowflake's Data Cloud is powered by an advanced data platform provided as a self-managed service.  |
------------------------------------------------------------------------------------------------------

输出¶

translation_text：如果 num_return_sequences 为 1，则为表示生成的翻译的字符串，或者是以 JSON 格式表示字典结果列表的字符串，每个字典均包含包括 translation_text 的字段。

示例：

---------------------------------------------------------------------------------------------------------------------------------
|"translation_text"                                                                                                             |
---------------------------------------------------------------------------------------------------------------------------------
|Le Cloud de données de Snowflake est alimenté par une plate-forme de données avancée fournie sous forme de service autogérés.  |
---------------------------------------------------------------------------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd

model = transformers.pipeline(
    task="translation",
    model="deepvk/kazRush-kk-ru",
)

text = "Иттерді кім шығарды?"


mv = registry.log_model(
    model=model,
    model_name="KAZRUSH_KK_RU",
)

mv.run(
    pd.DataFrame.from_records([{"inputs": text}]),
    # function_name="__call__", # Optional
)

Zero-shot 分类¶

“zero-shot-classification (link removed)”任务的管道具有以下输入和输出。

输入¶

sequences：包含要分类的文本的字符串。
candidate_labels：包含要应用于文本的标签的字符串列表。

示例：

-----------------------------------------------------------------------------------------
|"sequences"                                                       |"candidate_labels"  |
-----------------------------------------------------------------------------------------
|I have a problem with Snowflake that needs to be resolved asap!!  |[                   |
|                                                                  |  "urgent",         |
|                                                                  |  "not urgent"      |
|                                                                  |]                   |
|I have a problem with Snowflake that needs to be resolved asap!!  |[                   |
|                                                                  |  "English",        |
|                                                                  |  "Japanese"        |
|                                                                  |]                   |
-----------------------------------------------------------------------------------------

输出¶

sequence：输入字符串。
labels：表示已应用的标签的字符串列表。
scores：每个标签的浮点置信度分数列表。

示例：

--------------------------------------------------------------------------------------------------------------
|"sequence"                                                        |"labels"        |"scores"                |
--------------------------------------------------------------------------------------------------------------
|I have a problem with Snowflake that needs to be resolved asap!!  |[               |[                       |
|                                                                  |  "urgent",     |  0.9952737092971802,   |
|                                                                  |  "not urgent"  |  0.004726255778223276  |
|                                                                  |]               |]                       |
|I have a problem with Snowflake that needs to be resolved asap!!  |[               |[                       |
|                                                                  |  "Japanese",   |  0.5790848135948181,   |
|                                                                  |  "English"     |  0.42091524600982666   |
|                                                                  |]               |]                       |
--------------------------------------------------------------------------------------------------------------

文本生成¶

任务是“` text-generation <https://huggingface.co/docs/transformers/en/main_classes/pipelines#transformers.TextGenerationPipeline (link removed)>`_”的管道，其中 return_tensors 为 False 或未设置，具有以下输入和输出。

备注

文本生成管道，其中 return_tensors 是 True，不受支持。

输入¶

inputs：包含提示的字符串。

示例：

--------------------------------------------------------------------------------
|"inputs"                                                                      |
--------------------------------------------------------------------------------
|A descendant of the Lost City of Atlantis, who swam to Earth while saying, "  |
--------------------------------------------------------------------------------

输出¶

outputs：一个字符串，包含以 JSON 格式表示的结果对象的列表，每个对象都包含包括 generated_text 的字段。

示例：

------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|"outputs"                                                                                                                                                                                                 |
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
|[{"generated_text": "A descendant of the Lost City of Atlantis, who swam to Earth while saying, \"For my life, I don't know if I'm gonna land upon Earth.\"\n\nIn \"The Misfits\", in a flashback, wh...  |
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd

model = transformers.pipeline(
    task="text-generation",
    model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
)

mv = registry.log_model(
    model=model,
    model_name="TINYLLAMA",
)

text = "A descendant of the Lost City of Atlantis, who swam to Earth while saying,"
mv.run(
    pd.DataFrame.from_records([{"inputs": text}]),
    # function_name="__call__", # Optional
)

文本生成（兼容 OpenAI）¶

通过在记录模型时提供 snowflake.ml.model.openai_signatures.OPENAI_CHAT_SIGNATURE 签名，该模型将与 OpenAI API 兼容。这允许用户向模型传递 openai.client.ChatCompletion 样式请求。

备注

文本生成管道，其中 return_tensors 是 True，不受支持。

输入¶

messages：包含要发送到模型的消息的字典列表。
max_completion_tokens：选择使用时默认使用的角色和仓库。生成的令牌的最大数量。
temperature：选择使用时默认使用的角色和仓库。用于生成的温度。
stop：选择使用时默认使用的角色和仓库。用于生成的停止序列。
n：选择使用时默认使用的角色和仓库。要生成的代数。
stream：选择使用时默认使用的角色和仓库。是否流式传输生成。
top_p：选择使用时默认使用的角色和仓库。用于生成的最高 p 值。
frequency_penalty：选择使用时默认使用的角色和仓库。用于生成的频率损失。
presence_penalty：选择使用时默认使用的角色和仓库。用于生成的存在惩罚。

示例：

-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| messages                                                                                                                                                                                          |   max_completion_tokens |   temperature | stop   |   n | stream   |   top_p |   frequency_penalty |  presence_penalty |
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| [{'role': 'system', 'content': 'Complete the sentence.'}, {'role': 'user', 'content': [{'type': 'text', 'text': 'A descendant of the Lost City of Atlantis, who swam to Earth while saying, '}]}] |                     250 |           0.9 |        |   3 | False    |       1 |                 0.1 |               0.2 |
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

输出¶

outputs：一个字符串，包含以 JSON 格式表示的结果对象的列表，每个对象都包含包括 generated_text 的字段。

示例：

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| id           | object          |     created | model                                      | choices                                                                                                                                      |  usage                                                               |
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| chatcmpl-... | chat.completion | 1.76912e+09 | /shared/model/model/models/TINYLLAMA/model | [{'finish_reason': 'stop', 'index': 0, 'logprobs': None, 'message': {'content': 'The descendant is not actually ...', 'role': 'assistant'}}] | {'completion_tokens': 399, 'prompt_tokens': 52, 'total_tokens': 451} |
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

代码示例¶

import transformers
import pandas as pd
from snowflake.ml.model import openai_signatures

model = transformers.pipeline(
    task="text-generation",
    model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
)


mv = registry.log_model(
    model=model,
    model_name="TINYLLAMA",
    signatures=openai_signatures.OPENAI_CHAT_SIGNATURE,
)

# create a pd.DataFrame with openai.client.chat.completion arguments
x_df = pd.DataFrame.from_records(
    [
        {
            "messages": [
                {
                    "role": "system",
                    "content": [
                        {
                            "type": "text",
                            "text": "Complete the sentence.",
                        }
                    ],
                },
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": "A descendant of the Lost City of Atlantis, who swam to Earth while saying, ",
                        }
                    ],
                },
            ],
            "max_completion_tokens": 250,
            "temperature": 0.9,
            "stop": None,
            "n": 3,
            "stream": False,
            "top_p": 1.0,
            "frequency_penalty": 0.1,
            "presence_penalty": 0.2,
        }
    ],
)

# OpenAI Chat Completion compatible output
output_df = mv.run(X=x_df)