explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-21 01:21:58 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update default config for OpenAI models.

Browse Source
This commit is contained in:
Raphael Mitsch 2023-08-11 13:34:44 +02:00
parent 45af8a5dcf
commit 2021bbd804
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
website/docs/api/large-language-models.mdx
View File

@ -754,7 +754,7 @@ OpenAI's `gpt-4` model family.
| Argument | Description |
| ----------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"gpt-4"`. ~~Literal["gpt-4", "gpt-4-0314", "gpt-4-32k", "gpt-4-32k-0314"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -775,7 +775,7 @@ OpenAI's `gpt-3-5` model family.
| Argument | Description |
| ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"gpt-3.5-turbo"`. ~~Literal["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-0613-16k"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -796,7 +796,7 @@ OpenAI's `text-davinci` model family.
| Argument | Description |
| ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"text-davinci-003"`. ~~Literal["text-davinci-002", "text-davinci-003"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 1000, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -817,7 +817,7 @@ OpenAI's `code-davinci` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"code-davinci-002"`. ~~Literal["code-davinci-002"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -838,7 +838,7 @@ OpenAI's `text-curie` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"text-curie-001"`. ~~Literal["text-curie-001"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -859,7 +859,7 @@ OpenAI's `text-babbage` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"text-babbage-001"`. ~~Literal["text-babbage-001"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -880,7 +880,7 @@ OpenAI's `text-ada` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"text-ada-001"`. ~~Literal["text-ada-001"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -901,7 +901,7 @@ OpenAI's `davinci` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"davinci"`. ~~Literal["davinci"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -922,7 +922,7 @@ OpenAI's `curie` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"curie"`. ~~Literal["curie"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -943,7 +943,7 @@ OpenAI's `babbage` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"babbage"`. ~~Literal["babbage"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |
@ -964,7 +964,7 @@ OpenAI's `ada` model family.
| Argument | Description |
| ----------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Model name, i. e. any supported variant for this particular model. Defaults to `"ada"`. ~~Literal["ada"]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{}`. ~~Dict[Any, Any]~~ |
| `config` | Further configuration passed on to the model. Defaults to `{"max_tokens": 500, "temperature": 0}`. ~~Dict[Any, Any]~~ |
| `strict` | If `True`, raises an error if the LLM API returns a malformed response. Otherwise, return the error responses as is. Defaults to `True`. ~~bool~~ |
| `max_tries` | Max. number of tries for API request. Defaults to `3`. ~~int~~ |
| `timeout` | Timeout for API request in seconds. Defaults to `30`. ~~int~~ |