Mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-06-07 19:40:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
5c69dd155f
LocalAI/backend/python/transformers/backend_pb2.py

62 lines
9.6 KiB
Python
Raw Normal View History

feat: add initial AutoGPTQ backend implementation
2023-08-07 20:39:10 +00:00
# -*- coding: utf-8 -*-
# Generated by the protocol buffer compiler. DO NOT EDIT!
# source: backend.proto
Bump vLLM version + more options when loading models in vLLM (#1782) * Bump vLLM version to 0.3.2 * Add vLLM model loading options * Remove transformers-exllama * Fix install exllama
2024-03-01 21:48:53 +00:00
# Protobuf Python Version: 4.25.1
feat: add initial AutoGPTQ backend implementation
2023-08-07 20:39:10 +00:00
"""Generated protocol buffer code."""
from google.protobuf import descriptor as _descriptor
from google.protobuf import descriptor_pool as _descriptor_pool
from google.protobuf import symbol_database as _symbol_database
from google.protobuf.internal import builder as _builder
# @@protoc_insertion_point(imports)
_sym_db = _symbol_database.Default()
Bump vLLM version + more options when loading models in vLLM (#1782) * Bump vLLM version to 0.3.2 * Add vLLM model loading options * Remove transformers-exllama * Fix install exllama
2024-03-01 21:48:53 +00:00
DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\rbackend.proto\x12\x07\x62\x61\x63kend\"\x0f\n\rHealthMessage\"\xa6\x06\n\x0ePredictOptions\x12\x0e\n\x06Prompt\x18\x01 \x01(\t\x12\x0c\n\x04Seed\x18\x02 \x01(\x05\x12\x0f\n\x07Threads\x18\x03 \x01(\x05\x12\x0e\n\x06Tokens\x18\x04 \x01(\x05\x12\x0c\n\x04TopK\x18\x05 \x01(\x05\x12\x0e\n\x06Repeat\x18\x06 \x01(\x05\x12\r\n\x05\x42\x61tch\x18\x07 \x01(\x05\x12\r\n\x05NKeep\x18\x08 \x01(\x05\x12\x13\n\x0bTemperature\x18\t \x01(\x02\x12\x0f\n\x07Penalty\x18\n \x01(\x02\x12\r\n\x05\x46\x31\x36KV\x18\x0b \x01(\x08\x12\x11\n\tDebugMode\x18\x0c \x01(\x08\x12\x13\n\x0bStopPrompts\x18\r \x03(\t\x12\x11\n\tIgnoreEOS\x18\x0e \x01(\x08\x12\x19\n\x11TailFreeSamplingZ\x18\x0f \x01(\x02\x12\x10\n\x08TypicalP\x18\x10 \x01(\x02\x12\x18\n\x10\x46requencyPenalty\x18\x11 \x01(\x02\x12\x17\n\x0fPresencePenalty\x18\x12 \x01(\x02\x12\x10\n\x08Mirostat\x18\x13 \x01(\x05\x12\x13\n\x0bMirostatETA\x18\x14 \x01(\x02\x12\x13\n\x0bMirostatTAU\x18\x15 \x01(\x02\x12\x12\n\nPenalizeNL\x18\x16 \x01(\x08\x12\x11\n\tLogitBias\x18\x17 \x01(\t\x12\r\n\x05MLock\x18\x19 \x01(\x08\x12\x0c\n\x04MMap\x18\x1a \x01(\x08\x12\x16\n\x0ePromptCacheAll\x18\x1b \x01(\x08\x12\x15\n\rPromptCacheRO\x18\x1c \x01(\x08\x12\x0f\n\x07Grammar\x18\x1d \x01(\t\x12\x0f\n\x07MainGPU\x18\x1e \x01(\t\x12\x13\n\x0bTensorSplit\x18\x1f \x01(\t\x12\x0c\n\x04TopP\x18 \x01(\x02\x12\x17\n\x0fPromptCachePath\x18! \x01(\t\x12\r\n\x05\x44\x65\x62ug\x18\" \x01(\x08\x12\x17\n\x0f\x45mbeddingTokens\x18# \x03(\x05\x12\x12\n\nEmbeddings\x18$ \x01(\t\x12\x14\n\x0cRopeFreqBase\x18% \x01(\x02\x12\x15\n\rRopeFreqScale\x18& \x01(\x02\x12\x1b\n\x13NegativePromptScale\x18\' \x01(\x02\x12\x16\n\x0eNegativePrompt\x18( \x01(\t\x12\x0e\n\x06NDraft\x18) \x01(\x05\x12\x0e\n\x06Images\x18* \x03(\t\"\x18\n\x05Reply\x12\x0f\n\x07message\x18\x01 \x01(\x0c\"\xb0\x08\n\x0cModelOptions\x12\r\n\x05Model\x18\x01 \x01(\t\x12\x13\n\x0b\x43ontextSize\x18\x02 \x01(\x05\x12\x0c\n\x04Seed\x18\x03 \x01(\x05\x12\x0e\n\x06NBatch\x18\x04 \x01(\x05\x12\x11\n\tF16Memory\x18\x05 \x01(\x08\x12\r\n\x05MLock\x18\x06 \x01(\x08\x12\x0c\n\x04MMap\x18\x07 \x01(\x08\x12\x11\n\tVocabOnly\x18\x08 \x01(\x08\x12\x0f\n\x07LowVRAM\x18\t \x01(\x08\x12\x12\n\nEmbeddings\x18\n \x01(\x08\x12\x0c\n\x04NUMA\x18\x0b \x01(\x08\x12\x12\n\nNGPULayers\x18\x0c \x01(\x05\x12\x0f\n\x07MainGPU\x18\r \x01(\t\x12\x13\n\x0bTensorSplit\x18\x0e \x01(\t\x12\x0f\n\x07Threads\x18\x0f \x01(\x05\x12\x19\n\x11LibrarySearchPath\x18\x10 \x01(\t\x12\x14\n\x0cRopeFreqBase\x18\x11 \x01(\x02\x12\x15\n\rRopeFreqScale\x18\x12 \x01(\x02\x12\x12\n\nRMSNormEps\x18\x13 \x01(\x02\x12\x0c\n\x04NGQA\x18\x14 \x01(\x05\x12\x11\n\tModelFile\x18\x15 \x01(\t\x12\x0e\n\x06\x44\x65vice\x18\x16 \x01(\t\x12\x11\n\tUseTriton\x18\x17 \x01(\x08\x12\x15\n\rModelBaseName\x18\x18 \x01(\t\x12\x18\n\x10UseFastTokenizer\x18\x19 \x01(\x08\x12\x14\n\x0cPipelineType\x18\x1a \x01(\t\x12\x15\n\rSchedulerType\x18\x1b \x01(\t\x12\x0c\n\x04\x43UDA\x18\x1c \x01(\x08\x12\x10\n\x08\x43\x46GScale\x18\x1d \x01(\x02\x12\x0f\n\x07IMG2IMG\x18\x1e \x01(\x08\x12\x11\n\tCLIPModel\x18\x1f \x01(\t\x12\x15\n\rCLIPSubfolder\x18 \x01(\t\x12\x10\n\x08\x43LIPSkip\x18! \x01(\x05\x12\x12\n\nControlNet\x18\x30 \x01(\t\x12\x11\n\tTokenizer\x18\" \x01(\t\x12\x10\n\x08LoraBase\x18# \x01(\t\x12\x13\n\x0bLoraAdapter\x18$ \x01(\t\x12\x11\n\tLoraScale\x18* \x01(\x02\x12\x11\n\tNoMulMatQ\x18% \x01(\x08\x12\x12\n\nDraftModel\x18\' \x01(\t\x12\x11\n\tAudioPath\x18& \x01(\t\x12\x14\n\x0cQuantization\x18( \x01(\t\x12\x1c\n\x14GPUMemoryUtilization\x18\x32 \x01(\x02\x12\x17\n\x0fTrustRemoteCode\x18\x33 \x01(\x08\x12\x14\n\x0c\x45nforceEager\x18\x34 \x01(\x08\x12\x11\n\tSwapSpace\x18\x35 \x01(\x05\x12\x13\n\x0bMaxModelLen\x18\x36 \x01(\x05\x12\x0e\n\x06MMProj\x18) \x01(\t\x12\x13\n\x0bRopeScaling\x18+ \x01(\t\x12\x15\n\rYarnExtFactor\x18, \x01(\x02\x12\x16\n\x0eYarnAttnFactor\x18- \x01(\x02\x12\x14\n\x0cYarnBetaFast\x18. \x01(\x02\x12\x14\n\x0cYarnBetaSlow\x18/ \x01(\x02\x12\x0c\n\x04Type\x18\x31 \x01(\t\"*\n\x06Result\x12\x0f\n\x07message\x18\x01 \x01(\t\x12\x0f\n\x07success\x18\x02 \x
feat: add initial AutoGPTQ backend implementation
2023-08-07 20:39:10 +00:00
_globals = globals()
_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'backend_pb2', _globals)
if _descriptor._USE_C_DESCRIPTORS == False:
Bump vLLM version + more options when loading models in vLLM (#1782) * Bump vLLM version to 0.3.2 * Add vLLM model loading options * Remove transformers-exllama * Fix install exllama
2024-03-01 21:48:53 +00:00
_globals['DESCRIPTOR']._options = None
_globals['DESCRIPTOR']._serialized_options = b'\n\031io.skynet.localai.backendB\016LocalAIBackendP\001Z+github.com/go-skynet/LocalAI/pkg/grpc/proto'
_globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._options = None
_globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_options = b'8\001'
feat: add initial AutoGPTQ backend implementation
2023-08-07 20:39:10 +00:00
_globals['_HEALTHMESSAGE']._serialized_start=26
_globals['_HEALTHMESSAGE']._serialized_end=41
_globals['_PREDICTOPTIONS']._serialized_start=44
:fire: add LaVA support and GPT vision API, Multiple requests for llama.cpp, return JSON types (#1254) * wip * wip * Make it functional Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip * Small fixups * do not inject space on role encoding, encode img at beginning of messages Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add examples/config defaults * Add include dir of current source dir * cleanup * fixes Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups * Revert "fixups" This reverts commit f1a4731ccadf7226c6589d6d39131376f0811625. * fixes Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-11-11 12:14:59 +00:00
_globals['_PREDICTOPTIONS']._serialized_end=850
_globals['_REPLY']._serialized_start=852
_globals['_REPLY']._serialized_end=876
_globals['_MODELOPTIONS']._serialized_start=879
Bump vLLM version + more options when loading models in vLLM (#1782) * Bump vLLM version to 0.3.2 * Add vLLM model loading options * Remove transformers-exllama * Fix install exllama
2024-03-01 21:48:53 +00:00
_globals['_MODELOPTIONS']._serialized_end=1951
_globals['_RESULT']._serialized_start=1953
_globals['_RESULT']._serialized_end=1995
_globals['_EMBEDDINGRESULT']._serialized_start=1997
_globals['_EMBEDDINGRESULT']._serialized_end=2034
_globals['_TRANSCRIPTREQUEST']._serialized_start=2036
_globals['_TRANSCRIPTREQUEST']._serialized_end=2103
_globals['_TRANSCRIPTRESULT']._serialized_start=2105
_globals['_TRANSCRIPTRESULT']._serialized_end=2183
_globals['_TRANSCRIPTSEGMENT']._serialized_start=2185
_globals['_TRANSCRIPTSEGMENT']._serialized_end=2274
_globals['_GENERATEIMAGEREQUEST']._serialized_start=2277
_globals['_GENERATEIMAGEREQUEST']._serialized_end=2492
_globals['_TTSREQUEST']._serialized_start=2494
_globals['_TTSREQUEST']._serialized_end=2548
_globals['_TOKENIZATIONRESPONSE']._serialized_start=2550
_globals['_TOKENIZATIONRESPONSE']._serialized_end=2604
_globals['_MEMORYUSAGEDATA']._serialized_start=2607
_globals['_MEMORYUSAGEDATA']._serialized_end=2749
_globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_start=2701
_globals['_MEMORYUSAGEDATA_BREAKDOWNENTRY']._serialized_end=2749
_globals['_STATUSRESPONSE']._serialized_start=2752
_globals['_STATUSRESPONSE']._serialized_end=2925
_globals['_STATUSRESPONSE_STATE']._serialized_start=2858
_globals['_STATUSRESPONSE_STATE']._serialized_end=2925
_globals['_BACKEND']._serialized_start=2928
_globals['_BACKEND']._serialized_end=3556
feat: add initial AutoGPTQ backend implementation
2023-08-07 20:39:10 +00:00
# @@protoc_insertion_point(module_scope)
Reference in New Issue Copy Permalink