explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-27 08:29:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into docs/llm

Browse Source
This commit is contained in:
svlandeg 2023-09-07 11:13:50 +02:00
commit ae7f64f48c
4 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
website/docs/api/large-language-models.mdx
View File

@ -602,7 +602,7 @@ on an upstream NER component for entities extraction.
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ | | `labels` | List of labels or str of comma-separated list of labels. ~~Union[List[str], str]~~ |
| `template` | Custom prompt template to send to LLM model. Defaults to [`rel.v3.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/rel.v1.jinja). ~~str~~ | | `template` | Custom prompt template to send to LLM model. Defaults to [`rel.v3.jinja`](https://github.com/explosion/spacy-llm/blob/main/spacy_llm/tasks/templates/rel.v1.jinja). ~~str~~ |
| `label_description` | Dictionary providing a description for each relation label. Defaults to `None`. ~~Optional[Dict[str, str]]~~ | | `label_definitions` | Dictionary providing a description for each relation label. Defaults to `None`. ~~Optional[Dict[str, str]]~~ |
| `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ | | `examples` | Optional function that generates examples for few-shot learning. Defaults to `None`. ~~Optional[Callable[[], Iterable[Any]]]~~ |
| `normalizer` | Function that normalizes the labels as returned by the LLM. If `None`, falls back to `spacy.LowercaseNormalizer.v1`. Defaults to `None`. ~~Optional[Callable[[str], str]]~~ | | `normalizer` | Function that normalizes the labels as returned by the LLM. If `None`, falls back to `spacy.LowercaseNormalizer.v1`. Defaults to `None`. ~~Optional[Callable[[str], str]]~~ |
| `verbose` | If set to `True`, warnings will be generated when the LLM returns invalid responses. Defaults to `False`. ~~bool~~ | | `verbose` | If set to `True`, warnings will be generated when the LLM returns invalid responses. Defaults to `False`. ~~bool~~ |
@ -621,6 +621,7 @@ supports `.yml`, `.yaml`, `.json` and `.jsonl`.
[components.llm.task] [components.llm.task]
@llm_tasks = "spacy.REL.v1" @llm_tasks = "spacy.REL.v1"
labels = ["LivesIn", "Visits"] labels = ["LivesIn", "Visits"]
[components.llm.task.examples] [components.llm.task.examples]
@misc = "spacy.FewShotReader.v1" @misc = "spacy.FewShotReader.v1"
path = "rel_examples.jsonl" path = "rel_examples.jsonl"

2
website/docs/usage/large-language-models.mdx
View File

@ -184,7 +184,7 @@ nlp.add_pipe(
"labels": ["PERSON", "ORGANISATION", "LOCATION"] "labels": ["PERSON", "ORGANISATION", "LOCATION"]
}, },
"model": { "model": {
"@llm_models": "spacy.gpt-3.5.v1", "@llm_models": "spacy.GPT-3-5.v1",
}, },
}, },
) )

21
website/docs/usage/training.mdx
View File

@ -180,7 +180,7 @@ Some of the main advantages and features of spaCy's training config are:
Under the hood, the config is parsed into a dictionary. It's divided into Under the hood, the config is parsed into a dictionary. It's divided into
sections and subsections, indicated by the square brackets and dot notation. For sections and subsections, indicated by the square brackets and dot notation. For
example, `[training]` is a section and `[training.batch_size]` a subsection. example, `[training]` is a section and `[training.batcher]` a subsection.
Subsections can define values, just like a dictionary, or use the `@` syntax to Subsections can define values, just like a dictionary, or use the `@` syntax to
refer to [registered functions](#config-functions). This allows the config to refer to [registered functions](#config-functions). This allows the config to
not just define static settings, but also construct objects like architectures, not just define static settings, but also construct objects like architectures,
@ -254,7 +254,7 @@ For cases like this, you can set additional command-line options starting with
block. block.
```bash ```bash
$ python -m spacy train config.cfg --paths.train ./corpus/train.spacy --paths.dev ./corpus/dev.spacy --training.batch_size 128 $ python -m spacy train config.cfg --paths.train ./corpus/train.spacy --paths.dev ./corpus/dev.spacy --training.max_epochs 3
``` ```
Only existing sections and values in the config can be overwritten. At the end Only existing sections and values in the config can be overwritten. At the end
@ -279,7 +279,7 @@ process. Environment variables **take precedence** over CLI overrides and values
defined in the config file. defined in the config file.
```bash ```bash
$ SPACY_CONFIG_OVERRIDES="--system.gpu_allocator pytorch --training.batch_size 128" ./your_script.sh $ SPACY_CONFIG_OVERRIDES="--system.gpu_allocator pytorch --training.max_epochs 3" ./your_script.sh
``` ```
### Reading from standard input {id="config-stdin"} ### Reading from standard input {id="config-stdin"}
@ -578,16 +578,17 @@ now-updated model to the predicted docs.
The training configuration defined in the config file doesn't have to only The training configuration defined in the config file doesn't have to only
consist of static values. Some settings can also be **functions**. For instance, consist of static values. Some settings can also be **functions**. For instance,
the `batch_size` can be a number that doesn't change, or a schedule, like a the batch size can be a number that doesn't change, or a schedule, like a
sequence of compounding values, which has shown to be an effective trick (see sequence of compounding values, which has shown to be an effective trick (see
[Smith et al., 2017](https://arxiv.org/abs/1711.00489)). [Smith et al., 2017](https://arxiv.org/abs/1711.00489)).
```ini {title="With static value"} ```ini {title="With static value"}
[training] [training.batcher]
batch_size = 128 @batchers = "spacy.batch_by_words.v1"
size = 3000
``` ```
To refer to a function instead, you can make `[training.batch_size]` its own To refer to a function instead, you can make `[training.batcher.size]` its own
section and use the `@` syntax to specify the function and its arguments – in section and use the `@` syntax to specify the function and its arguments – in
this case [`compounding.v1`](https://thinc.ai/docs/api-schedules#compounding) this case [`compounding.v1`](https://thinc.ai/docs/api-schedules#compounding)
defined in the [function registry](/api/top-level#registry). All other values defined in the [function registry](/api/top-level#registry). All other values
@ -606,7 +607,7 @@ from your configs.
> optimizer. > optimizer.
```ini {title="With registered function"} ```ini {title="With registered function"}
[training.batch_size] [training.batcher.size]
@schedules = "compounding.v1" @schedules = "compounding.v1"
start = 100 start = 100
stop = 1000 stop = 1000
@ -1027,14 +1028,14 @@ def my_custom_schedule(start: int = 1, factor: float = 1.001):
``` ```
In your config, you can now reference the schedule in the In your config, you can now reference the schedule in the
`[training.batch_size]` block via `@schedules`. If a block contains a key `[training.batcher.size]` block via `@schedules`. If a block contains a key
starting with an `@`, it's interpreted as a reference to a function. All other starting with an `@`, it's interpreted as a reference to a function. All other
settings in the block will be passed to the function as keyword arguments. Keep settings in the block will be passed to the function as keyword arguments. Keep
in mind that the config shouldn't have any hidden defaults and all arguments on in mind that the config shouldn't have any hidden defaults and all arguments on
the functions need to be represented in the config. the functions need to be represented in the config.
```ini {title="config.cfg (excerpt)"} ```ini {title="config.cfg (excerpt)"}
[training.batch_size] [training.batcher.size]
@schedules = "my_custom_schedule.v1" @schedules = "my_custom_schedule.v1"
start = 2 start = 2
factor = 1.005 factor = 1.005

6
website/meta/universe.json
View File

@ -2806,7 +2806,7 @@
"", "",
"# see github repo for examples on sentence-transformers and Huggingface", "# see github repo for examples on sentence-transformers and Huggingface",
"nlp = spacy.load('en_core_web_md')", "nlp = spacy.load('en_core_web_md')",
"nlp.add_pipe(\"text_categorizer\", ", "nlp.add_pipe(\"classy_classification\", ",
" config={", " config={",
" \"data\": data,", " \"data\": data,",
" \"model\": \"spacy\"", " \"model\": \"spacy\"",
@ -3010,8 +3010,8 @@
"# Load the spaCy language model:", "# Load the spaCy language model:",
"nlp = spacy.load(\"en_core_web_sm\")", "nlp = spacy.load(\"en_core_web_sm\")",
"", "",
"# Add the \"text_categorizer\" pipeline component to the spaCy model, and configure it with SetFit parameters:", "# Add the \"spacy_setfit\" pipeline component to the spaCy model, and configure it with SetFit parameters:",
"nlp.add_pipe(\"text_categorizer\", config={", "nlp.add_pipe(\"spacy_setfit\", config={",
" \"pretrained_model_name_or_path\": \"paraphrase-MiniLM-L3-v2\",", " \"pretrained_model_name_or_path\": \"paraphrase-MiniLM-L3-v2\",",
" \"setfit_trainer_args\": {", " \"setfit_trainer_args\": {",
" \"train_dataset\": train_dataset", " \"train_dataset\": train_dataset",