Spaces:
Runtime error
Runtime error
File size: 8,657 Bytes
ed4d993 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 |
# flake8: noqa
from typing import Any, AsyncIterator, Dict, Iterator, List, Optional, Union
from langchain_core.pydantic_v1 import root_validator
from langchain_core.callbacks import (
AsyncCallbackManagerForLLMRun,
CallbackManagerForLLMRun,
)
from langchain_core.language_models.llms import LLM
from langchain_community.llms.utils import enforce_stop_tokens
from langchain_core.outputs import GenerationChunk
class DeepSparse(LLM):
"""Neural Magic DeepSparse LLM interface.
To use, you should have the ``deepsparse`` or ``deepsparse-nightly``
python package installed. See https://github.com/neuralmagic/deepsparse
This interface let's you deploy optimized LLMs straight from the
[SparseZoo](https://sparsezoo.neuralmagic.com/?useCase=text_generation)
Example:
.. code-block:: python
from langchain_community.llms import DeepSparse
llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
""" # noqa: E501
pipeline: Any #: :meta private:
model: str
"""The path to a model file or directory or the name of a SparseZoo model stub."""
model_config: Optional[Dict[str, Any]] = None
"""Keyword arguments passed to the pipeline construction.
Common parameters are sequence_length, prompt_sequence_length"""
generation_config: Union[None, str, Dict] = None
"""GenerationConfig dictionary consisting of parameters used to control
sequences generated for each prompt. Common parameters are:
max_length, max_new_tokens, num_return_sequences, output_scores,
top_p, top_k, repetition_penalty."""
streaming: bool = False
"""Whether to stream the results, token by token."""
@property
def _identifying_params(self) -> Dict[str, Any]:
"""Get the identifying parameters."""
return {
"model": self.model,
"model_config": self.model_config,
"generation_config": self.generation_config,
"streaming": self.streaming,
}
@property
def _llm_type(self) -> str:
"""Return type of llm."""
return "deepsparse"
@root_validator()
def validate_environment(cls, values: Dict) -> Dict:
"""Validate that ``deepsparse`` package is installed."""
try:
from deepsparse import Pipeline
except ImportError:
raise ImportError(
"Could not import `deepsparse` package. "
"Please install it with `pip install deepsparse[llm]`"
)
model_config = values["model_config"] or {}
values["pipeline"] = Pipeline.create(
task="text_generation",
model_path=values["model"],
**model_config,
)
return values
def _call(
self,
prompt: str,
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> str:
"""Generate text from a prompt.
Args:
prompt: The prompt to generate text from.
stop: A list of strings to stop generation when encountered.
Returns:
The generated text.
Example:
.. code-block:: python
from langchain_community.llms import DeepSparse
llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
llm.invoke("Tell me a joke.")
"""
if self.streaming:
combined_output = ""
for chunk in self._stream(
prompt=prompt, stop=stop, run_manager=run_manager, **kwargs
):
combined_output += chunk.text
text = combined_output
else:
text = (
self.pipeline(sequences=prompt, **self.generation_config)
.generations[0]
.text
)
if stop is not None:
text = enforce_stop_tokens(text, stop)
return text
async def _acall(
self,
prompt: str,
stop: Optional[List[str]] = None,
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> str:
"""Generate text from a prompt.
Args:
prompt: The prompt to generate text from.
stop: A list of strings to stop generation when encountered.
Returns:
The generated text.
Example:
.. code-block:: python
from langchain_community.llms import DeepSparse
llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
llm.invoke("Tell me a joke.")
"""
if self.streaming:
combined_output = ""
async for chunk in self._astream(
prompt=prompt, stop=stop, run_manager=run_manager, **kwargs
):
combined_output += chunk.text
text = combined_output
else:
text = (
self.pipeline(sequences=prompt, **self.generation_config)
.generations[0]
.text
)
if stop is not None:
text = enforce_stop_tokens(text, stop)
return text
def _stream(
self,
prompt: str,
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> Iterator[GenerationChunk]:
"""Yields results objects as they are generated in real time.
It also calls the callback manager's on_llm_new_token event with
similar parameters to the OpenAI LLM class method of the same name.
Args:
prompt: The prompt to pass into the model.
stop: Optional list of stop words to use when generating.
Returns:
A generator representing the stream of tokens being generated.
Yields:
A dictionary like object containing a string token.
Example:
.. code-block:: python
from langchain_community.llms import DeepSparse
llm = DeepSparse(
model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none",
streaming=True
)
for chunk in llm.stream("Tell me a joke",
stop=["'","\n"]):
print(chunk, end='', flush=True) # noqa: T201
"""
inference = self.pipeline(
sequences=prompt, streaming=True, **self.generation_config
)
for token in inference:
chunk = GenerationChunk(text=token.generations[0].text)
yield chunk
if run_manager:
run_manager.on_llm_new_token(token=chunk.text)
async def _astream(
self,
prompt: str,
stop: Optional[List[str]] = None,
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> AsyncIterator[GenerationChunk]:
"""Yields results objects as they are generated in real time.
It also calls the callback manager's on_llm_new_token event with
similar parameters to the OpenAI LLM class method of the same name.
Args:
prompt: The prompt to pass into the model.
stop: Optional list of stop words to use when generating.
Returns:
A generator representing the stream of tokens being generated.
Yields:
A dictionary like object containing a string token.
Example:
.. code-block:: python
from langchain_community.llms import DeepSparse
llm = DeepSparse(
model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none",
streaming=True
)
for chunk in llm.stream("Tell me a joke",
stop=["'","\n"]):
print(chunk, end='', flush=True) # noqa: T201
"""
inference = self.pipeline(
sequences=prompt, streaming=True, **self.generation_config
)
for token in inference:
chunk = GenerationChunk(text=token.generations[0].text)
yield chunk
if run_manager:
await run_manager.on_llm_new_token(token=chunk.text)
|