langchain.llms.rwkv.RWKV

class langchain.llms.rwkv.RWKV(*, cache: Optional[bool] = None, verbose: bool = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, callback_manager: Optional[BaseCallbackManager] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, model: str, tokens_path: str, strategy: str = 'cpu fp32', rwkv_verbose: bool = True, temperature: float = 1.0, top_p: float = 0.5, penalty_alpha_frequency: float = 0.4, penalty_alpha_presence: float = 0.4, CHUNK_LEN: int = 256, max_tokens_per_generation: int = 256, client: Any = None, tokenizer: Any = None, pipeline: Any = None, model_tokens: Any = None, model_state: Any = None)

Bases: LLM, BaseModel

RWKV language models.

To use, you should have the rwkv python package installed, the pre-trained model file, and the model’s config information.

Example

from langchain.llms import RWKV
model = RWKV(model="./models/rwkv-3b-fp16.bin", strategy="cpu fp32")

# Simplest invocation
response = model("Once upon a time, ")

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param CHUNK_LEN: int = 256

Batch size for prompt processing.

param cache: Optional[bool] = None

param callback_manager: Optional[BaseCallbackManager] = None

param callbacks: Callbacks = None

param max_tokens_per_generation: int = 256

Maximum number of tokens to generate.

param metadata: Optional[Dict[str, Any]] = None

Metadata to add to the run trace.

param model: str [Required]

Path to the pre-trained RWKV model file.

param penalty_alpha_frequency: float = 0.4

Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim..

param penalty_alpha_presence: float = 0.4

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics..

param rwkv_verbose: bool = True

Print debug information.

param strategy: str = 'cpu fp32'

Token context window.

param tags: Optional[List[str]] = None

Tags to add to the run trace.

param temperature: float = 1.0

The temperature to use for sampling.

param tokens_path: str [Required]

Path to the RWKV tokens file.

param top_p: float = 0.5

The top-p value to use for sampling.

param verbose: bool [Optional]

Whether to print out response text.

__call__(prompt: str, stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) → str

Check Cache and run the LLM on the given prompt and input.

async abatch(inputs: List[Union[PromptValue, str, List[BaseMessage]]], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, max_concurrency: Optional[int] = None, **kwargs: Any) → List[str]

async agenerate(prompts: List[str], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, *, tags: Optional[Union[List[str], List[List[str]]]] = None, metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, **kwargs: Any) → LLMResult

Run the LLM on the given prompt and input.

async agenerate_prompt(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, **kwargs: Any) → LLMResult

Asynchronously pass a sequence of prompts and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:

1. take advantage of batched calls,

2. need more output from the model than just the top generated value,

3. are building chains that are agnostic to the underlying language model

   type (e.g., pure text completion models vs chat models).

Parameters

• prompts – List of PromptValues. A PromptValue is an object that can be converted to match the format of any language model (string for pure text generation models and BaseMessages for chat models).

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• callbacks – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

async ainvoke(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → str

async apredict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → str

Asynchronously pass a string to the model and return a string prediction.

Use this method when calling pure text generation models and only the top

candidate generation is needed.

Parameters

• text – String input to pass to the model.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a string.

async apredict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → BaseMessage

Asynchronously pass messages to the model and return a message prediction.

Use this method when calling chat models and only the top

candidate generation is needed.

Parameters

• messages – A sequence of chat messages corresponding to a single model input.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a message.

async astream(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → AsyncIterator[str]

batch(inputs: List[Union[PromptValue, str, List[BaseMessage]]], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, max_concurrency: Optional[int] = None, **kwargs: Any) → List[str]

dict(**kwargs: Any) → Dict

Return a dictionary of the LLM.

generate(prompts: List[str], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, *, tags: Optional[Union[List[str], List[List[str]]]] = None, metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, **kwargs: Any) → LLMResult

Run the LLM on the given prompt and input.

generate_prompt(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, **kwargs: Any) → LLMResult

Pass a sequence of prompts to the model and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:

1. take advantage of batched calls,

2. need more output from the model than just the top generated value,

3. are building chains that are agnostic to the underlying language model

   type (e.g., pure text completion models vs chat models).

Parameters

• prompts – List of PromptValues. A PromptValue is an object that can be converted to match the format of any language model (string for pure text generation models and BaseMessages for chat models).

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• callbacks – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

get_num_tokens(text: str) → int

Get the number of tokens present in the text.

Useful for checking if an input will fit in a model’s context window.

Parameters

text – The string input to tokenize.

Returns

The integer number of tokens in the text.

get_num_tokens_from_messages(messages: List[BaseMessage]) → int

Get the number of tokens in the messages.

Useful for checking if an input will fit in a model’s context window.

Parameters

messages – The message inputs to tokenize.

Returns

The sum of the number of tokens across the messages.

get_token_ids(text: str) → List[int]

Return the ordered ids of the tokens in a text.

Parameters

text – The string input to tokenize.

Returns

A list of ids corresponding to the tokens in the text, in order they occur

in the text.

invoke(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → str

predict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → str

Pass a single string input to the model and return a string prediction.

Use this method when passing in raw text. If you want to pass in specific

types of chat messages, use predict_messages.

Parameters

• text – String input to pass to the model.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a string.

predict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → BaseMessage

Pass a message sequence to the model and return a message prediction.

Use this method when passing in chat messages. If you want to pass in raw text,

use predict.

Parameters

• messages – A sequence of chat messages corresponding to a single model input.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a message.

validator raise_deprecation  »  all fields

Raise deprecation warning if callback_manager is used.

run_rnn(_tokens: List[str], newline_adj: int = 0) → Any

rwkv_generate(prompt: str) → str

save(file_path: Union[Path, str]) → None

Save the LLM.

Parameters

file_path – Path to file to save the LLM to.

Example: .. code-block:: python

llm.save(file_path=”path/llm.yaml”)

validator set_verbose  »  verbose

If verbose is None, set it.

This allows users to pass in None as verbose to access the global setting.

stream(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → Iterator[str]

to_json() → Union[SerializedConstructor, SerializedNotImplemented]

to_json_not_implemented() → SerializedNotImplemented

validator validate_environment  »  all fields

Validate that the python package exists in the environment.

property lc_attributes: Dict

Return a list of attribute names that should be included in the serialized kwargs. These attributes must be accepted by the constructor.

property lc_namespace: List[str]

Return the namespace of the langchain object. eg. [“langchain”, “llms”, “openai”]

property lc_secrets: Dict[str, str]

Return a map of constructor argument names to secret ids. eg. {“openai_api_key”: “OPENAI_API_KEY”}

property lc_serializable: bool

Return whether or not the class is serializable.

model Config

Bases: object

Configuration for this pydantic object.

extra = 'forbid'

Examples using RWKV

• RWKV-4