104 lines
4.0 KiB
Python
104 lines
4.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
# Adapted from
|
|
# https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/qwen2/modeling_qwen2.py
|
|
# Copyright 2024 The Qwen team.
|
|
# Copyright 2023 The vLLM team.
|
|
# Copyright 2022 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.
|
|
"""Inference-only Qwen2 model compatible with HuggingFace weights."""
|
|
from vllm.model_executor.models.qwen2 import *
|
|
|
|
|
|
class CosyVoice2ForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
|
|
packed_modules_mapping = {
|
|
"qkv_proj": [
|
|
"q_proj",
|
|
"k_proj",
|
|
"v_proj",
|
|
],
|
|
"gate_up_proj": [
|
|
"gate_proj",
|
|
"up_proj",
|
|
],
|
|
}
|
|
|
|
def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
|
|
super().__init__()
|
|
config = vllm_config.model_config.hf_config
|
|
quant_config = vllm_config.quant_config
|
|
lora_config = vllm_config.lora_config
|
|
|
|
self.config = config
|
|
self.lora_config = lora_config
|
|
|
|
self.quant_config = quant_config
|
|
self.model = Qwen2Model(vllm_config=vllm_config,
|
|
prefix=maybe_prefix(prefix, "model"))
|
|
|
|
if get_pp_group().is_last_rank:
|
|
if config.tie_word_embeddings:
|
|
self.lm_head = self.model.embed_tokens
|
|
else:
|
|
self.lm_head = ParallelLMHead(config.vocab_size,
|
|
config.hidden_size,
|
|
True,
|
|
quant_config=quant_config,
|
|
prefix=maybe_prefix(
|
|
prefix, "lm_head"))
|
|
else:
|
|
self.lm_head = PPMissingLayer()
|
|
|
|
self.logits_processor = LogitsProcessor(config.vocab_size)
|
|
|
|
self.make_empty_intermediate_tensors = (
|
|
self.model.make_empty_intermediate_tensors)
|
|
|
|
def get_input_embeddings(self, input_ids: torch.Tensor) -> torch.Tensor:
|
|
return self.model.get_input_embeddings(input_ids)
|
|
|
|
def forward(
|
|
self,
|
|
input_ids: torch.Tensor,
|
|
positions: torch.Tensor,
|
|
intermediate_tensors: Optional[IntermediateTensors] = None,
|
|
inputs_embeds: Optional[torch.Tensor] = None,
|
|
) -> Union[torch.Tensor, IntermediateTensors]:
|
|
hidden_states = self.model(input_ids, positions, intermediate_tensors,
|
|
inputs_embeds)
|
|
return hidden_states
|
|
|
|
def compute_logits(
|
|
self,
|
|
hidden_states: torch.Tensor,
|
|
sampling_metadata: SamplingMetadata,
|
|
) -> Optional[torch.Tensor]:
|
|
logits = self.logits_processor(self.lm_head, hidden_states,
|
|
sampling_metadata, self.lm_head.bias)
|
|
return logits
|
|
|
|
def load_weights(self, weights: Iterable[tuple[str,
|
|
torch.Tensor]]) -> set[str]:
|
|
loader = AutoWeightsLoader(
|
|
self,
|
|
skip_prefixes=(["lm_head."]
|
|
if self.config.tie_word_embeddings else None),
|
|
)
|
|
return loader.load_weights(weights)
|