explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

Few spacy-llm doc fixes (#12969)

Browse Source 
* fix construction example

* shorten task-specific factory list

* small edits to HF models

* small edit to API models

* typo

* fix space

Co-authored-by: Raphael Mitsch <r.mitsch@outlook.com>

---------

Co-authored-by: Raphael Mitsch <r.mitsch@outlook.com>
This commit is contained in:
Sofie Van Landeghem 2023-09-08 11:35:38 +02:00 committed by GitHub
parent def7013eec
commit 013762be41
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
website/docs/api/large-language-models.mdx
View File

@ -19,26 +19,20 @@ prototyping** and **prompting**, and turning unstructured responses into
An LLM component is implemented through the `LLMWrapper` class. It is accessible
through a generic `llm`
[component factory](https://spacy.io/usage/processing-pipelines#custom-components-factories)
as well as through task-specific component factories:
- `llm_ner`
- `llm_spancat`
- `llm_rel`
- `llm_textcat`
- `llm_sentiment`
- `llm_summarization`
as well as through task-specific component factories: `llm_ner`, `llm_spancat`, `llm_rel`,
`llm_textcat`, `llm_sentiment` and `llm_summarization`.
### LLMWrapper.\_\_init\_\_ {id="init",tag="method"}
> #### Example
>
> ```python
> # Construction via add_pipe with default GPT3.5 model and NER task
> # Construction via add_pipe with the default GPT 3.5 model and an explicitly defined task
> config = {"task": {"@llm_tasks": "spacy.NER.v3", "labels": ["PERSON", "ORGANISATION", "LOCATION"]}}
> llm = nlp.add_pipe("llm")
> llm = nlp.add_pipe("llm", config=config)
>
> # Construction via add_pipe with task-specific factory and default GPT3.5 model
> parser = nlp.add_pipe("llm-ner", config=config)
> # Construction via add_pipe with a task-specific factory and default GPT3.5 model
> llm = nlp.add_pipe("llm-ner")
>
> # Construction from class
> from spacy_llm.pipeline import LLMWrapper
@ -956,6 +950,8 @@ provider's API.
> config = {"temperature": 0.0}
> ```
Currently, these models are provided as part of the core library:
| Model | Provider | Supported names | Default name | Default config |
| ----------------------------- | --------- | ---------------------------------------------------------------------------------------- | ---------------------- | ------------------------------------ |
| `spacy.GPT-4.v1` | OpenAI | `["gpt-4", "gpt-4-0314", "gpt-4-32k", "gpt-4-32k-0314"]` | `"gpt-4"` | `{}` |
@ -1036,6 +1032,8 @@ These models all take the same parameters:
> name = "llama2-7b-hf"
> ```
Currently, these models are provided as part of the core library:
| Model | Provider | Supported names | HF directory |
| -------------------- | --------------- | ------------------------------------------------------------------------------------------------------------ | -------------------------------------- |
| `spacy.Dolly.v1` | Databricks | `["dolly-v2-3b", "dolly-v2-7b", "dolly-v2-12b"]` | https://huggingface.co/databricks |
@ -1044,8 +1042,6 @@ These models all take the same parameters:
| `spacy.StableLM.v1` | Stability AI | `["stablelm-base-alpha-3b", "stablelm-base-alpha-7b", "stablelm-tuned-alpha-3b", "stablelm-tuned-alpha-7b"]` | https://huggingface.co/stabilityai |
| `spacy.OpenLLaMA.v1` | OpenLM Research | `["open_llama_3b", "open_llama_7b", "open_llama_7b_v2", "open_llama_13b"]` | https://huggingface.co/openlm-research |
See the "HF directory" for more details on each of the models.
Note that Hugging Face will download the model the first time you use it - you
can
[define the cached directory](https://huggingface.co/docs/huggingface_hub/main/en/guides/manage-cache)