vLLM¶
vLLM
¶
Bases: LLM
, CudaDevicePlacementMixin
vLLM
library LLM implementation.
Attributes:
Name | Type | Description |
---|---|---|
model |
str
|
the model Hugging Face Hub repo id or a path to a directory containing the model weights and configuration files. |
dtype |
str
|
the data type to use for the model. Defaults to |
trust_remote_code |
bool
|
whether to trust the remote code when loading the model. Defaults
to |
quantization |
Optional[str]
|
the quantization mode to use for the model. Defaults to |
revision |
Optional[str]
|
the revision of the model to load. Defaults to |
tokenizer |
Optional[str]
|
the tokenizer Hugging Face Hub repo id or a path to a directory containing
the tokenizer files. If not provided, the tokenizer will be loaded from the
model directory. Defaults to |
tokenizer_mode |
Literal['auto', 'slow']
|
the mode to use for the tokenizer. Defaults to |
tokenizer_revision |
Optional[str]
|
the revision of the tokenizer to load. Defaults to |
skip_tokenizer_init |
bool
|
whether to skip the initialization of the tokenizer. Defaults
to |
chat_template |
Optional[str]
|
a chat template that will be used to build the prompts before
sending them to the model. If not provided, the chat template defined in the
tokenizer config will be used. If not provided and the tokenizer doesn't have
a chat template, then ChatML template will be used. Defaults to |
structured_output |
Optional[RuntimeParameter[OutlinesStructuredOutputType]]
|
a dictionary containing the structured output configuration or if more
fine-grained control is needed, an instance of |
seed |
int
|
the seed to use for the random number generator. Defaults to |
extra_kwargs |
Optional[RuntimeParameter[Dict[str, Any]]]
|
additional dictionary of keyword arguments that will be passed to the
|
_model |
Optional[LLM]
|
the |
_tokenizer |
Optional[PreTrainedTokenizer]
|
the tokenizer instance used to format the prompt before passing it to
the |
References
- https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/llm.py
Runtime parameters
extra_kwargs
: additional dictionary of keyword arguments that will be passed to theLLM
class ofvllm
library.
Examples:
Generate text:
```python
from distilabel.llms import vLLM
# You can pass a custom chat_template to the model
llm = vLLM(
model="prometheus-eval/prometheus-7b-v2.0",
chat_template="[INST] {{ messages[0]"content" }}\n{{ messages[1]"content" }}[/INST]",
)
llm.load()
# Call the model
output = llm.generate(inputs=[[{"role": "user", "content": "Hello world!"}]])
```
Generate structured data:
```python
from pathlib import Path
from distilabel.llms import vLLM
class User(BaseModel):
name: str
last_name: str
id: int
llm = vLLM(
model="prometheus-eval/prometheus-7b-v2.0"
structured_output={"format": "json", "schema": Character},
)
llm.load()
# Call the model
output = llm.generate(inputs=[[{"role": "user", "content": "Create a user profile for the following marathon"}]])
```
Source code in src/distilabel/llms/vllm.py
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
|
model_name: str
property
¶
Returns the model name used for the LLM.
generate(inputs, num_generations=1, max_new_tokens=128, frequency_penalty=0.0, presence_penalty=0.0, temperature=1.0, top_p=1.0, top_k=-1, extra_sampling_params=None)
¶
Generates num_generations
responses for each input using the text generation
pipeline.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
inputs |
List[FormattedInput]
|
a list of inputs in chat format to generate responses for. |
required |
num_generations |
int
|
the number of generations to create per input. Defaults to
|
1
|
max_new_tokens |
int
|
the maximum number of new tokens that the model will generate.
Defaults to |
128
|
frequency_penalty |
float
|
the repetition penalty to use for the generation. Defaults
to |
0.0
|
presence_penalty |
float
|
the presence penalty to use for the generation. Defaults to
|
0.0
|
temperature |
float
|
the temperature to use for the generation. Defaults to |
1.0
|
top_p |
float
|
the top-p value to use for the generation. Defaults to |
1.0
|
top_k |
int
|
the top-k value to use for the generation. Defaults to |
-1
|
extra_sampling_params |
Optional[Dict[str, Any]]
|
dictionary with additional arguments to be passed to
the |
None
|
Returns:
Type | Description |
---|---|
List[GenerateOutput]
|
A list of lists of strings containing the generated responses for each input. |
Source code in src/distilabel/llms/vllm.py
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 |
|
load()
¶
Loads the vLLM
model using either the path or the Hugging Face Hub repository id.
Additionally, this method also sets the chat_template
for the tokenizer, so as to properly
parse the list of OpenAI formatted inputs using the expected format by the model, otherwise, the
default value is ChatML format, unless explicitly provided.
Source code in src/distilabel/llms/vllm.py
prepare_input(input)
¶
Prepares the input by applying the chat template to the input, which is formatted as an OpenAI conversation, and adding the generation prompt.