first commit
This commit is contained in:
xxl
parent
a59cc03f08
commit
f2c2596063
Binary file not shown.
70
README.md
70
README.md
|
|
@ -1,4 +1,70 @@
|
|||
# AquilaChat2-7B_a13670421562519552438590
|
||||
---
|
||||
license: other
|
||||
---
|
||||
|
||||
|
||||
AquilaChat2-7B
|
||||
|
||||
|
||||
|
||||
<h4 align="center">
|
||||
<p>
|
||||
<b>English</b> |
|
||||
<a href="https://huggingface.co/BAAI/AquilaChat2-7B/blob/main/README_zh.md">简体中文</a>
|
||||
</p>
|
||||
</h4>
|
||||
|
||||
|
||||
We opensource our **Aquila2** series, now including **Aquila2**, the base language models, namely **Aquila2-7B** and **Aquila2-34B**, as well as **AquilaChat2**, the chat models, namely **AquilaChat2-7B** and **AquilaChat2-34B**, as well as the long-text chat models, namely **AquilaChat2-7B-16k** and **AquilaChat2-34B-16k**
|
||||
|
||||
The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels.
|
||||
|
||||
## Quick Start AquilaChat2-7B（Chat model）
|
||||
|
||||
### 1. Inference
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
from transformers import BitsAndBytesConfig
|
||||
|
||||
device = torch.device("cuda:0")
|
||||
model_info = "BAAI/AquilaChat2-7B"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
|
||||
quantization_config=BitsAndBytesConfig(
|
||||
load_in_4bit=True,
|
||||
bnb_4bit_use_double_quant=True,
|
||||
bnb_4bit_quant_type="nf4",
|
||||
bnb_4bit_compute_dtype=torch.bfloat16,
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True, torch_dtype=torch.float16,
|
||||
# quantization_config=quantization_config, # Uncomment this line for 4bit quantization
|
||||
)
|
||||
model.eval()
|
||||
model.to(device)
|
||||
text = "请给出10个要到北京旅游的理由。"
|
||||
from predict import predict
|
||||
out = predict(model, text, tokenizer=tokenizer, max_gen_len=200, top_p=0.95,
|
||||
seed=1234, topk=100, temperature=0.9, sft=True, device=device,
|
||||
model_name="AquilaChat2-7B")
|
||||
print(out)
|
||||
```
|
||||
|
||||
|
||||
## License
|
||||
|
||||
Aquila2 series open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/AquilaChat2-7B/blob/main/BAAI-Aquila-Model-License%20-Agreement.pdf)
|
||||
|
||||
## Citation
|
||||
Feel free to cite the repo if you think Aquila2 is useful.
|
||||
|
||||
```python
|
||||
@misc{zhang2024aquila2technicalreport,
|
||||
title={Aquila2 Technical Report},
|
||||
author={Bo-Wen Zhang and Liangdong Wang and Jijie Li and Shuhao Gu and Xinya Wu and Zhengduo Zhang and Boyan Gao and Yulong Ao and Guang Liu},
|
||||
year={2024},
|
||||
eprint={2408.07410},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2408.07410},
|
||||
}
|
||||
```
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
---
|
||||
license: other
|
||||
---
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<h4 align="center">
|
||||
<p>
|
||||
<a href="https://huggingface.co/BAAI/AquilaChat2-7B/blob/main/README.md">English</a>
|
||||
<b>简体中文</b> |
|
||||
</p>
|
||||
</h4>
|
||||
|
||||
# 悟道·天鹰（Aquila2）
|
||||
|
||||
我们开源了我们的 **Aquila2** 系列，现在包括基础语言模型 **Aquila2-7B** 和 **Aquila2-34B** ，对话模型 **AquilaChat2-7B** 和 **AquilaChat2-34B**，长文本对话模型**AquilaChat2-7B-16k** 和 **AquilaChat2-34B-16k**
|
||||
|
||||
悟道 · 天鹰 Aquila 模型的更多细节将在官方技术报告中呈现。请关注官方渠道更新。
|
||||
|
||||
## 快速开始使用 AquilaChat2-7B
|
||||
|
||||
|
||||
## 使用方式/How to use
|
||||
|
||||
### 1. 推理/Inference
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
device = torch.device("cuda")
|
||||
model_info = "BAAI/AquilaChat2-7B"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True)
|
||||
model.eval()
|
||||
model.to(device)
|
||||
text = "请给出10个要到北京旅游的理由。"
|
||||
tokens = tokenizer.encode_plus(text)['input_ids']
|
||||
tokens = torch.tensor(tokens)[None,].to(device)
|
||||
stop_tokens = ["###", "[UNK]", "</s>"]
|
||||
with torch.no_grad():
|
||||
out = model.generate(tokens, do_sample=True, max_length=512, eos_token_id=100007, bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0]
|
||||
out = tokenizer.decode(out.cpu().numpy().tolist())
|
||||
print(out)
|
||||
```
|
||||
|
||||
|
||||
## 证书/License
|
||||
|
||||
Aquila2系列开源模型使用 [智源Aquila系列模型许可协议](https://huggingface.co/BAAI/Aquila2-70B/blob/main/BAAI-Aquila-Model-License-Agreement.pdf)
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
{
|
||||
"</s>": 100007,
|
||||
"<|LDWANG|>": 100002,
|
||||
"<|endofpiece|>": 100001,
|
||||
"<|startofpiece|>": 100000,
|
||||
"[CLS]": 100006,
|
||||
"[MASK]": 100003,
|
||||
"[gMASK]": 100004,
|
||||
"[sMASK]": 100005
|
||||
}
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
{
|
||||
"architectures": [
|
||||
"AquilaForCausalLM"
|
||||
],
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_aquila.AquilaConfig",
|
||||
"AutoModelForCausalLM": "modeling_aquila.AquilaForCausalLM"
|
||||
},
|
||||
"bos_token_id": 100006,
|
||||
"eos_token_id": 100007,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "aquila",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.31.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 100008
|
||||
}
|
||||
|
|
@ -0,0 +1 @@
|
|||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
|
|
@ -0,0 +1,128 @@
|
|||
# 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):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`AquilaModel`]. It is used to instantiate an Aquila
|
||||
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 Aquila-7B.
|
||||
|
||||
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 32000):
|
||||
Vocabulary size of the Aquila model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`AquilaModel`]
|
||||
hidden_size (`int`, *optional*, defaults to 4096):
|
||||
Dimension of the hidden representations.
|
||||
intermediate_size (`int`, *optional*, defaults to 11008):
|
||||
Dimension of the MLP representations.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 32):
|
||||
Number of hidden layers in the Transformer encoder.
|
||||
num_attention_heads (`int`, *optional*, defaults to 32):
|
||||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
||||
The non-linear activation function (function or string) in the decoder.
|
||||
max_position_embeddings (`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).
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
rms_norm_eps (`float`, *optional*, defaults to 1e-12):
|
||||
The epsilon used by the rms normalization layers.
|
||||
use_cache (`bool`, *optional*, defaults to `True`):
|
||||
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
||||
relevant if `config.is_decoder=True`.
|
||||
tie_word_embeddings(`bool`, *optional*, defaults to `False`):
|
||||
Whether to tie weight embeddings
|
||||
Example:
|
||||
|
||||
```python
|
||||
>>> from transformers import AquilaModel, AquilaConfig
|
||||
|
||||
>>> # Initializing a Aquila aquila-7b style configuration
|
||||
>>> configuration = AquilaConfig()
|
||||
|
||||
>>> # Initializing a model from the aquila-7b style configuration
|
||||
>>> model = AquilaModel(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
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=0.02,
|
||||
rms_norm_eps=1e-6,
|
||||
use_cache=True,
|
||||
pad_token_id=0,
|
||||
bos_token_id=1,
|
||||
eos_token_id=2,
|
||||
pretraining_tp=1,
|
||||
tie_word_embeddings=False,
|
||||
rope_theta=10000.0,
|
||||
rope_scaling=None,
|
||||
**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.pretraining_tp = pretraining_tp
|
||||
self.use_cache = use_cache
|
||||
self.rope_theta = rope_theta
|
||||
self.rope_scaling = rope_scaling
|
||||
|
||||
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,
|
||||
)
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 100006,
|
||||
"eos_token_id": 100007,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.31.0"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,446 @@
|
|||
"""
|
||||
Copied from https://github.com/lm-sys/FastChat.
|
||||
Later we will contribute our changes into it.
|
||||
"""
|
||||
import dataclasses
|
||||
from enum import auto, IntEnum
|
||||
from typing import List, Any, Dict
|
||||
import math
|
||||
from typing import List, Optional, Tuple, Union
|
||||
import random
|
||||
import numpy as np
|
||||
|
||||
import torch
|
||||
import torch.utils.checkpoint
|
||||
from torch import nn
|
||||
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
|
||||
|
||||
from transformers.activations import ACT2FN
|
||||
from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, SequenceClassifierOutputWithPast
|
||||
from transformers.modeling_utils import PreTrainedModel
|
||||
from transformers.utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
|
||||
from transformers import (
|
||||
LogitsProcessorList,
|
||||
MinLengthLogitsProcessor,
|
||||
TopKLogitsWarper,
|
||||
TemperatureLogitsWarper,
|
||||
TopPLogitsWarper,
|
||||
StoppingCriteriaList,
|
||||
MaxLengthCriteria,
|
||||
BitsAndBytesConfig,
|
||||
)
|
||||
|
||||
|
||||
|
||||
class SeparatorStyle(IntEnum):
|
||||
"""Separator styles."""
|
||||
|
||||
ADD_COLON_SINGLE = auto()
|
||||
ADD_COLON_TWO = auto()
|
||||
ADD_COLON_SPACE_SINGLE = auto()
|
||||
NO_COLON_SINGLE = auto()
|
||||
NO_COLON_TWO = auto()
|
||||
ADD_NEW_LINE_SINGLE = auto()
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
class Conversation:
|
||||
"""A class that manages prompt templates and keeps all conversation history."""
|
||||
|
||||
# The name of this template
|
||||
name: str
|
||||
# The template of the system prompt
|
||||
system_template: str = "{system_message}"
|
||||
# The system message
|
||||
system_message: str = ""
|
||||
# The names of two roles
|
||||
roles: List[str] = (("USER", "ASSISTANT"),)
|
||||
# All messages. Each item is (role, message).
|
||||
messages: List[List[str]] = ()
|
||||
# The number of few shot examples
|
||||
offset: int = 0
|
||||
# The separator style and configurations
|
||||
sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
|
||||
sep: str = "\n"
|
||||
sep2: str = None
|
||||
# Stop criteria (the default one is EOS token)
|
||||
stop_str: str = None
|
||||
# Stops generation if meeting any token in this list
|
||||
stop_token_ids: List[int] = None
|
||||
|
||||
def get_prompt(self) -> str:
|
||||
"""Get the prompt for generation."""
|
||||
system_prompt = self.system_template.format(system_message=self.system_message)
|
||||
if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
|
||||
ret = system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ": " + message + self.sep
|
||||
else:
|
||||
ret += role + ":"
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = system_prompt + seps[0]
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += role + ": " + message + seps[i % 2]
|
||||
else:
|
||||
ret += role + ":"
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
|
||||
ret = system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ": " + message + self.sep
|
||||
else:
|
||||
ret += role + ": " # must be end with a space
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
|
||||
ret = "" if system_prompt == "" else system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + "\n" + message + self.sep
|
||||
else:
|
||||
ret += role + "\n"
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
|
||||
ret = system_prompt
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + message + self.sep
|
||||
else:
|
||||
ret += role
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = system_prompt
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += role + message + seps[i % 2]
|
||||
else:
|
||||
ret += role
|
||||
return ret
|
||||
|
||||
def set_system_message(self, system_message: str):
|
||||
"""Set the system message."""
|
||||
self.system_message = system_message
|
||||
|
||||
def append_message(self, role: str, message: str):
|
||||
"""Append a new message."""
|
||||
self.messages.append([role, message])
|
||||
|
||||
def update_last_message(self, message: str):
|
||||
"""Update the last output.
|
||||
|
||||
The last message is typically set to be None when constructing the prompt,
|
||||
so we need to update it in-place after getting the response from a model.
|
||||
"""
|
||||
self.messages[-1][1] = message
|
||||
|
||||
def copy(self):
|
||||
return Conversation(
|
||||
name=self.name,
|
||||
system_template=self.system_template,
|
||||
system_message=self.system_message,
|
||||
roles=self.roles,
|
||||
messages=[[x, y] for x, y in self.messages],
|
||||
offset=self.offset,
|
||||
sep_style=self.sep_style,
|
||||
sep=self.sep,
|
||||
sep2=self.sep2,
|
||||
stop_str=self.stop_str,
|
||||
stop_token_ids=self.stop_token_ids,
|
||||
)
|
||||
|
||||
def dict(self):
|
||||
return {
|
||||
"template_name": self.name,
|
||||
"system_message": self.system_message,
|
||||
"roles": self.roles,
|
||||
"messages": self.messages,
|
||||
"offset": self.offset,
|
||||
}
|
||||
|
||||
|
||||
# A global registry for all conversation templates
|
||||
conv_templates: Dict[str, Conversation] = {}
|
||||
|
||||
|
||||
def register_conv_template(template: Conversation, override: bool = False):
|
||||
"""Register a new conversation template."""
|
||||
if not override:
|
||||
assert (
|
||||
template.name not in conv_templates
|
||||
), f"{template.name} has been registered."
|
||||
|
||||
conv_templates[template.name] = template
|
||||
|
||||
|
||||
def get_conv_template(name: str) -> Conversation:
|
||||
"""Get a conversation template."""
|
||||
return conv_templates[name].copy()
|
||||
|
||||
def get_conversation_template(model_path: str) -> Conversation:
|
||||
"""Get the default conversation template."""
|
||||
if "aquila-v1" in model_path:
|
||||
return get_conv_template("aquila-v1")
|
||||
elif "aquila-chat" in model_path:
|
||||
return get_conv_template("aquila-chat")
|
||||
elif "aquila-legacy" in model_path:
|
||||
return get_conv_template("aquila-legacy")
|
||||
else:
|
||||
return get_conv_template("aquila")
|
||||
|
||||
# AquilaChat default template
|
||||
# source: https://github.com/FlagAI-Open/FlagAI/blob/master/examples/Aquila/Aquila-chat/cyg_conversation.py
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="aquila-chat",
|
||||
system_message="A chat between a curious human and an artificial intelligence assistant. "
|
||||
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
|
||||
roles=("Human", "Assistant", "System"),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.ADD_COLON_SINGLE,
|
||||
sep="###",
|
||||
sep2="",
|
||||
stop_str=["###", "</s>", "[UNK]"],
|
||||
)
|
||||
)
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="aquila-legacy",
|
||||
system_message="A chat between a curious human and an artificial intelligence assistant. "
|
||||
"The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
|
||||
roles=("### Human: ", "### Assistant: ", "System"),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.NO_COLON_TWO,
|
||||
sep="\n",
|
||||
sep2="</s>",
|
||||
stop_str=["</s>", "[UNK]"],
|
||||
)
|
||||
)
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="aquila",
|
||||
system_message="A chat between a curious human and an artificial intelligence assistant. "
|
||||
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
|
||||
roles=("Human", "Assistant", "System"),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.ADD_COLON_TWO,
|
||||
sep="###",
|
||||
sep2="</s>",
|
||||
stop_str=["</s>", "[UNK]"],
|
||||
)
|
||||
)
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="aquila-v1",
|
||||
roles=("<|startofpiece|>", "<|endofpiece|>", ""),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.NO_COLON_TWO,
|
||||
sep="",
|
||||
sep2="</s>",
|
||||
stop_str=["</s>", "<|endoftext|>"],
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
print("aquila template:")
|
||||
conv = get_conv_template("aquila")
|
||||
conv.append_message(conv.roles[0], "Hello!")
|
||||
conv.append_message(conv.roles[1], "Hi!")
|
||||
conv.append_message(conv.roles[0], "How are you?")
|
||||
conv.append_message(conv.roles[1], None)
|
||||
print(conv.get_prompt())
|
||||
|
||||
print("\n")
|
||||
|
||||
print("aquila-chat template:")
|
||||
conv = get_conv_template("aquila-chat")
|
||||
conv.append_message(conv.roles[0], "Hello!")
|
||||
conv.append_message(conv.roles[1], "Hi!")
|
||||
conv.append_message(conv.roles[0], "How are you?")
|
||||
conv.append_message(conv.roles[1], None)
|
||||
print(conv.get_prompt())
|
||||
|
||||
print("\n")
|
||||
|
||||
print("aquila-v1 template:")
|
||||
conv = get_conv_template("aquila-v1")
|
||||
conv.append_message(conv.roles[0], "Hello!")
|
||||
conv.append_message(conv.roles[1], "Hi!")
|
||||
conv.append_message(conv.roles[0], "How are you?")
|
||||
conv.append_message(conv.roles[1], None)
|
||||
print(conv.get_prompt())
|
||||
|
||||
print("\n")
|
||||
|
||||
print("aquila-legacy template:")
|
||||
conv = get_conv_template("aquila-legacy")
|
||||
conv.append_message(conv.roles[0], "Hello!")
|
||||
conv.append_message(conv.roles[1], "Hi!")
|
||||
conv.append_message(conv.roles[0], "How are you?")
|
||||
conv.append_message(conv.roles[1], None)
|
||||
print(conv.get_prompt())
|
||||
|
||||
print("\n")
|
||||
|
||||
def set_random_seed(seed):
|
||||
"""Set random seed for reproducability."""
|
||||
if seed is not None and seed > 0:
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
torch.manual_seed(seed)
|
||||
|
||||
def covert_prompt_to_input_ids_with_history(text, history, tokenizer, max_token, convo_template="aquila-chat"):
|
||||
# aquila-chat as default
|
||||
conv = get_conv_template(convo_template)
|
||||
|
||||
conv.append_message(conv.roles[1], None)
|
||||
conv.append_message(conv.roles[0], text)
|
||||
|
||||
example = tokenizer.encode_plus(f"{conv.get_prompt()} ", None, max_length=None)['input_ids']
|
||||
|
||||
if history is None or not isinstance(history, list):
|
||||
history = []
|
||||
|
||||
while(len(history) > 0 and (len(example) < max_token)):
|
||||
tmp = history.pop()
|
||||
if tmp[0] == 'ASSISTANT':
|
||||
conv.append_message(conv.roles[1], tmp[1])
|
||||
else:
|
||||
conv.append_message(conv.roles[0], tmp[1])
|
||||
example = tokenizer.encode_plus(f"{conv.get_prompt()} ", None, max_length=None)['input_ids']
|
||||
|
||||
if len(example) >= max_token:
|
||||
conv.messages.pop()
|
||||
conv.messages = conv.messages[::-1]
|
||||
print('model in:', conv.get_prompt())
|
||||
example = tokenizer.encode_plus(f"{conv.get_prompt()} ", None, max_length=None)['input_ids']
|
||||
|
||||
return example
|
||||
|
||||
def predict(model, text, tokenizer=None,
|
||||
max_gen_len=200, top_p=0.95,
|
||||
seed=1234, topk=100,
|
||||
temperature=0.9,
|
||||
sft=True, convo_template = "",
|
||||
device = "cuda",
|
||||
model_name="AquilaChat2-7B",
|
||||
history=None,
|
||||
**kwargs):
|
||||
|
||||
vocab = tokenizer.get_vocab()
|
||||
|
||||
id2word = {v:k for k, v in vocab.items()}
|
||||
|
||||
|
||||
template_map = {"AquilaChat2-7B": "aquila-v1",
|
||||
"AquilaChat2-34B": "aquila-legacy",
|
||||
"AquilaChat2-7B-16K": "aquila",
|
||||
"AquilaChat2-34B-16K": "aquila"}
|
||||
if not convo_template:
|
||||
convo_template=template_map.get(model_name, "aquila-chat")
|
||||
|
||||
set_random_seed(seed)
|
||||
if temperature == 0:
|
||||
topk = 1
|
||||
temperature = 1.0
|
||||
if sft:
|
||||
tokens = covert_prompt_to_input_ids_with_history(text, history=history, tokenizer=tokenizer, max_token=2048, convo_template=convo_template)
|
||||
tokens = torch.tensor(tokens)[None,].to(device)
|
||||
else :
|
||||
tokens = tokenizer.encode_plus(text)["input_ids"]
|
||||
print(tokenizer.decode(tokens))
|
||||
tokens = torch.tensor(tokens)[None,].to(device)
|
||||
input_length = len(tokens[0])
|
||||
with torch.no_grad():
|
||||
|
||||
# instantiate logits processors
|
||||
logits_processor = LogitsProcessorList(
|
||||
[
|
||||
MinLengthLogitsProcessor(1, eos_token_id=100007),
|
||||
]
|
||||
)
|
||||
# instantiate logits processors
|
||||
logits_warper = LogitsProcessorList(
|
||||
[
|
||||
TopPLogitsWarper(top_p),
|
||||
TopKLogitsWarper(topk),
|
||||
TemperatureLogitsWarper(temperature),
|
||||
|
||||
]
|
||||
)
|
||||
|
||||
stopping_criteria = StoppingCriteriaList([MaxLengthCriteria(max_length=input_length + max_gen_len)])
|
||||
out = model.sample(
|
||||
tokens,
|
||||
logits_processor=logits_processor,
|
||||
logits_warper=logits_warper,
|
||||
stopping_criteria=stopping_criteria,
|
||||
return_dict_in_generate=True,
|
||||
output_scores=True,
|
||||
)
|
||||
|
||||
|
||||
# print(out)
|
||||
out_ids = out["sequences"][0][input_length:].cpu().numpy()
|
||||
|
||||
out_scores = out["scores"]
|
||||
|
||||
out_scores = torch.cat(out_scores, dim=0)
|
||||
out_scores = torch.nn.functional.softmax(out_scores, dim=-1).cpu().numpy()
|
||||
|
||||
probs = []
|
||||
for i in range(len(out_ids)):
|
||||
probs.append(float(out_scores[i][out_ids[i]]))
|
||||
|
||||
# print(f"probs is {probs}")
|
||||
|
||||
convert_tokens = []
|
||||
for t in out_ids:
|
||||
if t == 100006:
|
||||
convert_tokens.append("[CLS]")
|
||||
else :
|
||||
convert_tokens.append(id2word.get(t, "[unkonwn_token]"))
|
||||
|
||||
out_text = tokenizer.decode(out_ids.tolist())
|
||||
|
||||
|
||||
out = out_text
|
||||
|
||||
if "[UNK]" in out:
|
||||
special_index = out.index("[UNK]")
|
||||
out = out[:special_index]
|
||||
token_length = len(tokenizer.encode_plus(out)["input_ids"])
|
||||
convert_tokens = convert_tokens[:token_length]
|
||||
probs = probs[:token_length]
|
||||
|
||||
if "</s>" in out:
|
||||
special_index = out.index("</s>")
|
||||
out = out[: special_index]
|
||||
token_length = len(tokenizer.encode_plus(out)["input_ids"])
|
||||
convert_tokens = convert_tokens[:token_length]
|
||||
probs = probs[:token_length]
|
||||
|
||||
if len(out) > 0 and out[0] == " ":
|
||||
out = out[1:]
|
||||
|
||||
convert_tokens = convert_tokens[1:]
|
||||
probs = probs[1:]
|
||||
|
||||
if isinstance(history, list):
|
||||
# Update history
|
||||
history.insert(0, ('ASSISTANT', out))
|
||||
history.insert(0, ('USER', text))
|
||||
|
||||
return out
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,330 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 29182156800
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
{
|
||||
"bos_token": "[CLS]",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,10 @@
|
|||
{
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "[CLS]",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "</s>",
|
||||
"model_max_length": 2048,
|
||||
"padding_side": "right",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue