mirror of
https://github.com/datawhalechina/llms-from-scratch-cn.git
synced 2026-05-01 11:58:17 +08:00
add gptj
This commit is contained in:
kewei
parent
5293898b58
commit
daade3d142
202
Model_Architecture_Discussions/gptj/configuration_gptj.py
Normal file
202
Model_Architecture_Discussions/gptj/configuration_gptj.py
Normal file
@ -0,0 +1,202 @@
|
||||
"""GPT-J model configuration"""
|
||||
|
||||
from collections import OrderedDict
|
||||
from typing import Any, List, Mapping, Optional
|
||||
|
||||
from transformers import PreTrainedTokenizer, TensorType, is_torch_available
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.onnx import OnnxConfigWithPast, PatchingSpec
|
||||
from transformers.utils import logging
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class GPTJConfig(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`GPTJModel`]. It is used to instantiate a GPT-J
|
||||
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
||||
defaults will yield a similar configuration to that of the GPT-J
|
||||
[EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) architecture. Configuration objects inherit from
|
||||
[`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`]
|
||||
for more information.
|
||||
|
||||
Args:
|
||||
vocab_size (`int`, *optional*, defaults to 50400):
|
||||
Vocabulary size of the GPT-J model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`GPTJModel`].
|
||||
n_positions (`int`, *optional*, defaults to 2048):
|
||||
The maximum sequence length that this model might ever be used with. Typically set this to something large
|
||||
just in case (e.g., 512 or 1024 or 2048).
|
||||
n_embd (`int`, *optional*, defaults to 4096):
|
||||
Dimensionality of the embeddings and hidden states.
|
||||
n_layer (`int`, *optional*, defaults to 28):
|
||||
Number of hidden layers in the Transformer encoder.
|
||||
n_head (`int`, *optional*, defaults to 16):
|
||||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
rotary_dim (`int`, *optional*, defaults to 64):
|
||||
Number of dimensions in the embedding that Rotary Position Embedding is applied to.
|
||||
n_inner (`int`, *optional*, defaults to None):
|
||||
Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
|
||||
activation_function (`str`, *optional*, defaults to `"gelu_new"`):
|
||||
Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`.
|
||||
resid_pdrop (`float`, *optional*, defaults to 0.1):
|
||||
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
|
||||
embd_pdrop (`int`, *optional*, defaults to 0.1):
|
||||
The dropout ratio for the embeddings.
|
||||
attn_pdrop (`float`, *optional*, defaults to 0.1):
|
||||
The dropout ratio for the attention.
|
||||
layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
|
||||
The epsilon to use in the layer normalization layers.
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
use_cache (`bool`, *optional*, defaults to `True`):
|
||||
Whether or not the model should return the last key/values attentions (not used by all models).
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
>>> from transformers import GPTJModel, GPTJConfig
|
||||
|
||||
>>> # Initializing a GPT-J 6B configuration
|
||||
>>> configuration = GPTJConfig()
|
||||
|
||||
>>> # Initializing a model from the configuration
|
||||
>>> model = GPTJModel(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
|
||||
model_type = "gptj"
|
||||
attribute_map = {
|
||||
"max_position_embeddings": "n_positions",
|
||||
"hidden_size": "n_embd",
|
||||
"num_attention_heads": "n_head",
|
||||
"num_hidden_layers": "n_layer",
|
||||
}
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=50400,
|
||||
n_positions=2048,
|
||||
n_embd=4096,
|
||||
n_layer=28,
|
||||
n_head=16,
|
||||
rotary_dim=64,
|
||||
n_inner=None,
|
||||
activation_function="gelu_new",
|
||||
resid_pdrop=0.0,
|
||||
embd_pdrop=0.0,
|
||||
attn_pdrop=0.0,
|
||||
layer_norm_epsilon=1e-5,
|
||||
initializer_range=0.02,
|
||||
use_cache=True,
|
||||
bos_token_id=50256,
|
||||
eos_token_id=50256,
|
||||
tie_word_embeddings=False,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
self.n_positions = n_positions
|
||||
self.n_embd = n_embd
|
||||
self.n_layer = n_layer
|
||||
self.n_head = n_head
|
||||
self.n_inner = n_inner
|
||||
self.rotary_dim = rotary_dim
|
||||
self.activation_function = activation_function
|
||||
self.resid_pdrop = resid_pdrop
|
||||
self.embd_pdrop = embd_pdrop
|
||||
self.attn_pdrop = attn_pdrop
|
||||
self.layer_norm_epsilon = layer_norm_epsilon
|
||||
self.initializer_range = initializer_range
|
||||
self.use_cache = use_cache
|
||||
|
||||
self.bos_token_id = bos_token_id
|
||||
self.eos_token_id = eos_token_id
|
||||
|
||||
super().__init__(
|
||||
bos_token_id=bos_token_id, eos_token_id=eos_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs
|
||||
)
|
||||
|
||||
|
||||
# Copied from transformers.models.gpt2.configuration_gpt2.GPT2OnnxConfig
|
||||
class GPTJOnnxConfig(OnnxConfigWithPast):
|
||||
def __init__(
|
||||
self,
|
||||
config: PretrainedConfig,
|
||||
task: str = "default",
|
||||
patching_specs: List[PatchingSpec] = None,
|
||||
use_past: bool = False,
|
||||
):
|
||||
super().__init__(config, task=task, patching_specs=patching_specs, use_past=use_past)
|
||||
if not getattr(self._config, "pad_token_id", None):
|
||||
# TODO: how to do that better?
|
||||
self._config.pad_token_id = 0
|
||||
|
||||
@property
|
||||
def inputs(self) -> Mapping[str, Mapping[int, str]]:
|
||||
common_inputs = OrderedDict({"input_ids": {0: "batch", 1: "sequence"}})
|
||||
if self.use_past:
|
||||
self.fill_with_past_key_values_(common_inputs, direction="inputs")
|
||||
common_inputs["attention_mask"] = {0: "batch", 1: "past_sequence + sequence"}
|
||||
else:
|
||||
common_inputs["attention_mask"] = {0: "batch", 1: "sequence"}
|
||||
|
||||
return common_inputs
|
||||
|
||||
@property
|
||||
def num_layers(self) -> int:
|
||||
return self._config.n_layer
|
||||
|
||||
@property
|
||||
def num_attention_heads(self) -> int:
|
||||
return self._config.n_head
|
||||
|
||||
def generate_dummy_inputs(
|
||||
self,
|
||||
tokenizer: PreTrainedTokenizer,
|
||||
batch_size: int = -1,
|
||||
seq_length: int = -1,
|
||||
is_pair: bool = False,
|
||||
framework: Optional[TensorType] = None,
|
||||
) -> Mapping[str, Any]:
|
||||
common_inputs = super(OnnxConfigWithPast, self).generate_dummy_inputs(
|
||||
tokenizer, batch_size=batch_size, seq_length=seq_length, is_pair=is_pair, framework=framework
|
||||
)
|
||||
|
||||
# We need to order the input in the way they appears in the forward()
|
||||
ordered_inputs = OrderedDict({"input_ids": common_inputs["input_ids"]})
|
||||
|
||||
# Need to add the past_keys
|
||||
if self.use_past:
|
||||
if not is_torch_available():
|
||||
raise ValueError("Cannot generate dummy past_keys inputs without PyTorch installed.")
|
||||
else:
|
||||
import torch
|
||||
|
||||
batch, seqlen = common_inputs["input_ids"].shape
|
||||
# Not using the same length for past_key_values
|
||||
past_key_values_length = seqlen + 2
|
||||
past_shape = (
|
||||
batch,
|
||||
self.num_attention_heads,
|
||||
past_key_values_length,
|
||||
self._config.hidden_size // self.num_attention_heads,
|
||||
)
|
||||
ordered_inputs["past_key_values"] = [
|
||||
(torch.zeros(past_shape), torch.zeros(past_shape)) for _ in range(self.num_layers)
|
||||
]
|
||||
|
||||
ordered_inputs["attention_mask"] = common_inputs["attention_mask"]
|
||||
if self.use_past:
|
||||
mask_dtype = ordered_inputs["attention_mask"].dtype
|
||||
ordered_inputs["attention_mask"] = torch.cat(
|
||||
[ordered_inputs["attention_mask"], torch.ones(batch, past_key_values_length, dtype=mask_dtype)], dim=1
|
||||
)
|
||||
|
||||
return ordered_inputs
|
||||
|
||||
@property
|
||||
def default_onnx_opset(self) -> int:
|
||||
return 13
|
||||
272
Model_Architecture_Discussions/gptj/gptj.ipynb
Normal file
272
Model_Architecture_Discussions/gptj/gptj.ipynb
Normal file
@ -0,0 +1,272 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "c5cff513-7872-4207-8877-c1873a58545a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"env: HF_ENDPOINT=https://hf-mirror.com\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%env HF_ENDPOINT=https://hf-mirror.com"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "f4c95697-a706-4fd1-bdb5-27f5868d6839",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"# 设置 HF_HOME 环境变量 设置下载路径\n",
|
||||
"os.environ['HF_HOME'] = '/data1/ckw'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "25ca2fbc-b24a-4355-83cb-8e721616e9e7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "58c6aa1afc0a46f98744a945dec66497",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"pytorch_model.bin: 95%|#########4| 22.9G/24.2G [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/data1/ckw/micromamba/envs/kewei-ai/lib/python3.11/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()\n",
|
||||
" return self.fget.__get__(instance, owner)()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "bc686f2484084fe9873912c76867507d",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"tokenizer_config.json: 0%| | 0.00/248 [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "8338c634a3f74ba2a1b398f095802875",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"vocab.json: 0.00B [00:00, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "fad33fcd58a54a5ebe9dd4744ce238aa",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"merges.txt: 0.00B [00:00, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "73b96b47f93d48f2aac6a54116ad233f",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"tokenizer.json: 0.00B [00:00, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "c40d212bd261454583ef354c76f5df60",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"added_tokens.json: 0%| | 0.00/726 [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/vnd.jupyter.widget-view+json": {
|
||||
"model_id": "e29e924fccbc435cb6a222718510553d",
|
||||
"version_major": 2,
|
||||
"version_minor": 0
|
||||
},
|
||||
"text/plain": [
|
||||
"special_tokens_map.json: 0%| | 0.00/357 [00:00<?, ?B/s]"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
|
||||
"Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\nDataWhalechina is an organization founded at Shanghai Jiao Tong University that helps learners learn artificial intelligence.\\n\\nReferences\\n\\nExternal links'"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from transformers import AutoTokenizer\n",
|
||||
"from modeling_gptj import GPTJForCausalLM\n",
|
||||
"\n",
|
||||
"model = GPTJForCausalLM.from_pretrained(\"EleutherAI/gpt-j-6B\")#,force_download=True)\n",
|
||||
"tokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-j-6B\")\n",
|
||||
"\n",
|
||||
"prompt = '\\nDataWhalechina is an organization founded at Shanghai Jiao Tong University that helps learners learn artificial intelligence.'\n",
|
||||
"inputs = tokenizer(prompt, return_tensors=\"pt\")\n",
|
||||
"\n",
|
||||
"# Generate\n",
|
||||
"generate_ids = model.generate(inputs.input_ids, max_length=30)\n",
|
||||
"tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "40f99088-fc0e-45c1-b197-758c66cfc0ec",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
|
||||
"Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\nDataWhalechina is an organization founded at Shanghai Jiao Tong University that helps learners learn artificial intelligence.\\n\\nReferences\\n\\nExternal links\\n \\n\\nCategory:Chinese educational websites\\nCategory:Chinese companies established in 2016\\nCategory:Companies based in Shanghai\\nCategory:Educational technology companies of China\\nCategory:Internet properties established in 2016\\nCategory:Shanghai Jiao Tong University\\nCategory:2016 establishments in China'"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"generate_ids = model.generate(inputs.input_ids, max_length=300)\n",
|
||||
"tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "2944b3cc-1a4d-4577-a3b9-18fd0d3315a4",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
|
||||
"Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\nDataWhalechina is an organization founded at Shanghai Jiao Tong University that helps learners learn artificial intelligence.\\n\\nReferences\\n\\nExternal links\\n \\n\\nCategory:Chinese educational websites\\nCategory:Chinese companies established in 2016\\nCategory:Companies based in Shanghai\\nCategory:Educational technology companies of China\\nCategory:Internet properties established in 2016\\nCategory:Shanghai Jiao Tong University\\nCategory:2016 establishments in China'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"generate_ids = model.generate(inputs.input_ids, max_length=500)\n",
|
||||
"tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b07d7e01-672d-4abf-a6b8-720c4dbed783",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "kewei-ai",
|
||||
"language": "python",
|
||||
"name": "kewei-ai"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
1410
Model_Architecture_Discussions/gptj/modeling_gptj.py
Normal file
1410
Model_Architecture_Discussions/gptj/modeling_gptj.py
Normal file
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user