Spaces:
Running
on
Zero
Running
on
Zero
File size: 7,220 Bytes
39d2f14 597cecf 39d2f14 597cecf 39d2f14 597cecf 39d2f14 |
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 |
# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from .baichuan.model import BaichuanForCausalLM
from .bert.model import (BertForQuestionAnswering,
BertForSequenceClassification, BertModel,
RobertaForQuestionAnswering,
RobertaForSequenceClassification, RobertaModel)
from .bloom.model import BloomForCausalLM, BloomModel
from .chatglm.config import ChatGLMConfig
from .chatglm.model import ChatGLMForCausalLM, ChatGLMModel
from .cogvlm.config import CogVLMConfig
from .cogvlm.model import CogVLMForCausalLM
from .commandr.model import CohereForCausalLM
from .dbrx.config import DbrxConfig
from .dbrx.model import DbrxForCausalLM
from .deepseek_v1.model import DeepseekForCausalLM
from .deepseek_v2.model import DeepseekV2ForCausalLM
from .dit.model import DiT
from .eagle.model import EagleForCausalLM
from .enc_dec.model import DecoderModel, EncoderModel, WhisperEncoder
from .f5tts.model import F5TTS
from .falcon.config import FalconConfig
from .falcon.model import FalconForCausalLM, FalconModel
from .gemma.config import GEMMA2_ARCHITECTURE, GEMMA_ARCHITECTURE, GemmaConfig
from .gemma.model import GemmaForCausalLM
from .gpt.config import GPTConfig
from .gpt.model import GPTForCausalLM, GPTModel
from .gptj.config import GPTJConfig
from .gptj.model import GPTJForCausalLM, GPTJModel
from .gptneox.model import GPTNeoXForCausalLM, GPTNeoXModel
from .grok.model import GrokForCausalLM
from .llama.config import LLaMAConfig
from .llama.model import LLaMAForCausalLM, LLaMAModel
from .mamba.model import MambaForCausalLM
from .medusa.config import MedusaConfig
from .medusa.model import MedusaForCausalLm
from .mllama.model import MLLaMAModel
from .modeling_utils import (PretrainedConfig, PretrainedModel,
SpeculativeDecodingMode)
from .mpt.model import MPTForCausalLM, MPTModel
from .nemotron_nas.model import DeciLMForCausalLM
from .opt.model import OPTForCausalLM, OPTModel
from .phi3.model import Phi3ForCausalLM, Phi3Model
from .phi.model import PhiForCausalLM, PhiModel
from .qwen.model import QWenForCausalLM
from .recurrentgemma.model import RecurrentGemmaForCausalLM
from .redrafter.model import ReDrafterForCausalLM
__all__ = [
"BertModel",
"BertForQuestionAnswering",
"BertForSequenceClassification",
"RobertaModel",
"RobertaForQuestionAnswering",
"RobertaForSequenceClassification",
"BloomModel",
"BloomForCausalLM",
"DiT",
"DeepseekForCausalLM",
"FalconConfig",
"DeepseekV2ForCausalLM",
"FalconForCausalLM",
"FalconModel",
"GPTConfig",
"GPTModel",
"GPTForCausalLM",
"OPTForCausalLM",
"OPTModel",
"LLaMAConfig",
"LLaMAForCausalLM",
"LLaMAModel",
"MedusaConfig",
"MedusaForCausalLm",
"ReDrafterForCausalLM",
"GPTJConfig",
"GPTJModel",
"GPTJForCausalLM",
"GPTNeoXModel",
"GPTNeoXForCausalLM",
"PhiModel",
"PhiConfig",
"Phi3Model",
"Phi3Config",
"PhiForCausalLM",
"Phi3ForCausalLM",
"ChatGLMConfig",
"ChatGLMForCausalLM",
"ChatGLMModel",
"BaichuanForCausalLM",
"QWenConfigQWenForCausalLM",
"QWenModel",
"EncoderModel",
"DecoderModel",
"PretrainedConfig",
"PretrainedModel",
"WhisperEncoder",
"MambaForCausalLM",
"MambaConfig",
"MPTForCausalLM",
"MPTModel",
"SkyworkForCausalLM",
"GemmaConfig",
"GemmaForCausalLM",
"DbrxConfig",
"DbrxForCausalLM",
"RecurrentGemmaForCausalLM",
"CogVLMConfig",
"CogVLMForCausalLM",
"EagleForCausalLM",
"SpeculativeDecodingMode",
"CohereForCausalLM",
"MLLaMAModel",
"F5TTS",
]
MODEL_MAP = {
"GPT2LMHeadModel": GPTForCausalLM,
"GPT2LMHeadCustomModel": GPTForCausalLM,
"GPTBigCodeForCausalLM": GPTForCausalLM,
"Starcoder2ForCausalLM": GPTForCausalLM,
"FuyuForCausalLM": GPTForCausalLM,
"Kosmos2ForConditionalGeneration": GPTForCausalLM,
"JAISLMHeadModel": GPTForCausalLM,
"GPTForCausalLM": GPTForCausalLM,
"NemotronForCausalLM": GPTForCausalLM,
"OPTForCausalLM": OPTForCausalLM,
"BloomForCausalLM": BloomForCausalLM,
"RWForCausalLM": FalconForCausalLM,
"FalconForCausalLM": FalconForCausalLM,
"PhiForCausalLM": PhiForCausalLM,
"Phi3ForCausalLM": Phi3ForCausalLM,
"Phi3VForCausalLM": Phi3ForCausalLM,
"Phi3SmallForCausalLM": Phi3ForCausalLM,
"PhiMoEForCausalLM": Phi3ForCausalLM,
"MambaForCausalLM": MambaForCausalLM,
"GPTNeoXForCausalLM": GPTNeoXForCausalLM,
"GPTJForCausalLM": GPTJForCausalLM,
"MPTForCausalLM": MPTForCausalLM,
"GLMModel": ChatGLMForCausalLM,
"ChatGLMModel": ChatGLMForCausalLM,
"ChatGLMForCausalLM": ChatGLMForCausalLM,
"LlamaForCausalLM": LLaMAForCausalLM,
"ExaoneForCausalLM": LLaMAForCausalLM,
"MistralForCausalLM": LLaMAForCausalLM,
"MixtralForCausalLM": LLaMAForCausalLM,
"ArcticForCausalLM": LLaMAForCausalLM,
"Grok1ModelForCausalLM": GrokForCausalLM,
"InternLMForCausalLM": LLaMAForCausalLM,
"InternLM2ForCausalLM": LLaMAForCausalLM,
"MedusaForCausalLM": MedusaForCausalLm,
"ReDrafterForCausalLM": ReDrafterForCausalLM,
"BaichuanForCausalLM": BaichuanForCausalLM,
"BaiChuanForCausalLM": BaichuanForCausalLM,
"SkyworkForCausalLM": LLaMAForCausalLM,
GEMMA_ARCHITECTURE: GemmaForCausalLM,
GEMMA2_ARCHITECTURE: GemmaForCausalLM,
"QWenLMHeadModel": QWenForCausalLM,
"QWenForCausalLM": QWenForCausalLM,
"Qwen2ForCausalLM": QWenForCausalLM,
"Qwen2MoeForCausalLM": QWenForCausalLM,
"Qwen2ForSequenceClassification": QWenForCausalLM,
"Qwen2VLForConditionalGeneration": QWenForCausalLM,
"WhisperEncoder": WhisperEncoder,
"EncoderModel": EncoderModel,
"DecoderModel": DecoderModel,
"DbrxForCausalLM": DbrxForCausalLM,
"RecurrentGemmaForCausalLM": RecurrentGemmaForCausalLM,
"CogVLMForCausalLM": CogVLMForCausalLM,
"DiT": DiT,
"DeepseekForCausalLM": DeepseekForCausalLM,
"DeciLMForCausalLM": DeciLMForCausalLM,
"DeepseekV2ForCausalLM": DeepseekV2ForCausalLM,
"EagleForCausalLM": EagleForCausalLM,
"CohereForCausalLM": CohereForCausalLM,
"MllamaForConditionalGeneration": MLLaMAModel,
"BertForQuestionAnswering": BertForQuestionAnswering,
"BertForSequenceClassification": BertForSequenceClassification,
"BertModel": BertModel,
"RobertaModel": RobertaModel,
"RobertaForQuestionAnswering": RobertaForQuestionAnswering,
"RobertaForSequenceClassification": RobertaForSequenceClassification,
"F5TTS": F5TTS,
}
|