forked from abetlen/llama-cpp-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathsettings.py
More file actions
163 lines (156 loc) · 5.39 KB
/
settings.py
File metadata and controls
163 lines (156 loc) · 5.39 KB
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
import os
import multiprocessing
from typing import Optional, List, Literal
from pydantic import Field
from pydantic_settings import BaseSettings, SettingsConfigDict
import llama_cpp
# Disable warning for model and model_alias settings
BaseSettings.model_config['protected_namespaces'] = ()
class ModelSettings(BaseSettings):
model: str = Field(
description="The path to the model to use for generating completions."
)
model_alias: Optional[str] = Field(
default=None,
description="The alias of the model to use for generating completions.",
)
# Model Params
n_gpu_layers: int = Field(
default=0,
ge=-1,
description="The number of layers to put on the GPU. The rest will be on the CPU. Set -1 to move all to GPU.",
)
main_gpu: int = Field(
default=0,
ge=0,
description="Main GPU to use.",
)
tensor_split: Optional[List[float]] = Field(
default=None,
description="Split layers across multiple GPUs in proportion.",
)
vocab_only: bool = Field(
default=False, description="Whether to only return the vocabulary."
)
use_mmap: bool = Field(
default=llama_cpp.llama_mmap_supported(),
description="Use mmap.",
)
use_mlock: bool = Field(
default=llama_cpp.llama_mlock_supported(),
description="Use mlock.",
)
# Context Params
seed: int = Field(default=llama_cpp.LLAMA_DEFAULT_SEED, description="Random seed. -1 for random.")
n_ctx: int = Field(default=2048, ge=1, description="The context size.")
n_batch: int = Field(
default=512, ge=1, description="The batch size to use per eval."
)
n_threads: int = Field(
default=max(multiprocessing.cpu_count() // 2, 1),
ge=1,
description="The number of threads to use.",
)
n_threads_batch: int = Field(
default=max(multiprocessing.cpu_count() // 2, 1),
ge=0,
description="The number of threads to use when batch processing.",
)
rope_scaling_type: int = Field(
default=llama_cpp.LLAMA_ROPE_SCALING_UNSPECIFIED
)
rope_freq_base: float = Field(
default=0.0, description="RoPE base frequency"
)
rope_freq_scale: float = Field(
default=0.0, description="RoPE frequency scaling factor"
)
yarn_ext_factor: float = Field(
default=-1.0
)
yarn_attn_factor: float = Field(
default=1.0
)
yarn_beta_fast: float = Field(
default=32.0
)
yarn_beta_slow: float = Field(
default=1.0
)
yarn_orig_ctx: int = Field(
default=0
)
mul_mat_q: bool = Field(
default=True, description="if true, use experimental mul_mat_q kernels"
)
f16_kv: bool = Field(default=True, description="Whether to use f16 key/value.")
logits_all: bool = Field(default=True, description="Whether to return logits.")
embedding: bool = Field(default=True, description="Whether to use embeddings.")
# Sampling Params
last_n_tokens_size: int = Field(
default=64,
ge=0,
description="Last n tokens to keep for repeat penalty calculation.",
)
# LoRA Params
lora_base: Optional[str] = Field(
default=None,
description="Optional path to base model, useful if using a quantized base model and you want to apply LoRA to an f16 model."
)
lora_path: Optional[str] = Field(
default=None,
description="Path to a LoRA file to apply to the model.",
)
# Backend Params
numa: bool = Field(
default=False,
description="Enable NUMA support.",
)
# Chat Format Params
chat_format: str = Field(
default="llama-2",
description="Chat format to use.",
)
clip_model_path: Optional[str] = Field(
default=None,
description="Path to a CLIP model to use for multi-modal chat completion.",
)
# Cache Params
cache: bool = Field(
default=False,
description="Use a cache to reduce processing times for evaluated prompts.",
)
cache_type: Literal["ram", "disk"] = Field(
default="ram",
description="The type of cache to use. Only used if cache is True.",
)
cache_size: int = Field(
default=2 << 30,
description="The size of the cache in bytes. Only used if cache is True.",
)
# Misc
verbose: bool = Field(
default=True, description="Whether to print debug information."
)
class ServerSettings(BaseSettings):
model_config = SettingsConfigDict(env_file='.env', extra='ignore')
host: str = Field(default="localhost", description="Listen address")
port: int = Field(default=8000, description="Listen port")
interrupt_requests: bool = Field(
default=True,
description="Whether to interrupt requests when a new request is received.",
)
config: Optional[str] = Field(default=None, description="Path to config file")
plugins: Optional[str] = Field(default=None, description="Path to the plugins directory")
class Settings(ModelSettings):
model_config = SettingsConfigDict(env_file='model.env', extra='ignore')
models: Optional[List[ModelSettings]] = Field(
default = [],
description="Model configs, overwrites default config"
)
SETTINGS: Optional[ServerSettings] = None
def set_settings(settings: ServerSettings):
global SETTINGS
SETTINGS = settings
def get_settings():
yield SETTINGS