Migrate AquilaForCausalLM to LlamaForCausalLM (#2867)
This commit is contained in:
@@ -5,7 +5,6 @@ from transformers import AutoConfig, PretrainedConfig
|
||||
from vllm.transformers_utils.configs import *
|
||||
|
||||
_CONFIG_REGISTRY = {
|
||||
"aquila": AquilaConfig,
|
||||
"baichuan": BaiChuanConfig,
|
||||
"chatglm": ChatGLMConfig,
|
||||
"mpt": MPTConfig,
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
from vllm.transformers_utils.configs.aquila import AquilaConfig
|
||||
from vllm.transformers_utils.configs.baichuan import BaiChuanConfig
|
||||
from vllm.transformers_utils.configs.chatglm import ChatGLMConfig
|
||||
from vllm.transformers_utils.configs.mpt import MPTConfig
|
||||
@@ -9,7 +8,6 @@ from vllm.transformers_utils.configs.qwen import QWenConfig
|
||||
from vllm.transformers_utils.configs.falcon import RWConfig
|
||||
|
||||
__all__ = [
|
||||
"AquilaConfig",
|
||||
"BaiChuanConfig",
|
||||
"ChatGLMConfig",
|
||||
"MPTConfig",
|
||||
|
||||
@@ -1,69 +0,0 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2023 EleutherAI and the HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
|
||||
# and OPT implementations in this library. It has been modified from its
|
||||
# original forms to accommodate minor architectural differences compared
|
||||
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
|
||||
#
|
||||
# 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.
|
||||
""" Aquila model configuration"""
|
||||
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
|
||||
class AquilaConfig(PretrainedConfig):
|
||||
model_type = "aquila"
|
||||
keys_to_ignore_at_inference = ["past_key_values"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=100008,
|
||||
hidden_size=4096,
|
||||
intermediate_size=11008,
|
||||
num_hidden_layers=32,
|
||||
num_attention_heads=32,
|
||||
num_key_value_heads=None,
|
||||
hidden_act="silu",
|
||||
max_position_embeddings=2048,
|
||||
initializer_range=0.006,
|
||||
rms_norm_eps=1e-5,
|
||||
use_cache=True,
|
||||
pad_token_id=0,
|
||||
bos_token_id=1,
|
||||
eos_token_id=2,
|
||||
tie_word_embeddings=False,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.hidden_size = hidden_size
|
||||
self.intermediate_size = intermediate_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
# for backward compatibility
|
||||
if num_key_value_heads is None:
|
||||
num_key_value_heads = num_attention_heads
|
||||
|
||||
self.num_key_value_heads = num_key_value_heads
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.hidden_act = hidden_act
|
||||
self.initializer_range = initializer_range
|
||||
self.rms_norm_eps = rms_norm_eps
|
||||
self.use_cache = use_cache
|
||||
super().__init__(
|
||||
pad_token_id=pad_token_id,
|
||||
bos_token_id=bos_token_id,
|
||||
eos_token_id=eos_token_id,
|
||||
tie_word_embeddings=tie_word_embeddings,
|
||||
**kwargs,
|
||||
)
|
||||
Reference in New Issue
Block a user