初始化项目，由ModelHub XC社区提供模型
Model: OpenBuddy/openbuddy-falcon-7b-v6-bf16 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_name_or_path": "/data/output/final/",
|
||||
"alibi": false,
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"RWForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_RW.RWConfig",
|
||||
"AutoModel": "modelling_RW.RWModel",
|
||||
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM",
|
||||
"AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
|
||||
"AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
|
||||
"AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification"
|
||||
},
|
||||
"bias": false,
|
||||
"bos_token_id": 11,
|
||||
"eos_token_id": 11,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4544,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "RefinedWebModel",
|
||||
"multi_query": true,
|
||||
"n_head": 71,
|
||||
"n_layer": 32,
|
||||
"parallel_attn": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.30.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 70144
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework":"Pytorch","task":"text-generation"}
|
||||
79
configuration_RW.py
Normal file
79
configuration_RW.py
Normal file
@@ -0,0 +1,79 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2022 the Big Science Workshop and HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# 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.
|
||||
""" Bloom configuration"""
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class RWConfig(PretrainedConfig):
|
||||
model_type = "RefinedWebModel"
|
||||
keys_to_ignore_at_inference = ["past_key_values"]
|
||||
attribute_map = {
|
||||
"num_hidden_layers": "n_layer",
|
||||
"num_attention_heads": "n_head",
|
||||
}
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=250880,
|
||||
hidden_size=64,
|
||||
n_layer=2,
|
||||
n_head=8,
|
||||
layer_norm_epsilon=1e-5,
|
||||
initializer_range=0.02,
|
||||
use_cache=True,
|
||||
bos_token_id=1,
|
||||
eos_token_id=2,
|
||||
apply_residual_connection_post_layernorm=False,
|
||||
hidden_dropout=0.0,
|
||||
attention_dropout=0.0,
|
||||
multi_query=False,
|
||||
alibi=False,
|
||||
bias=False,
|
||||
parallel_attn=False,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
# Backward compatibility with n_embed kwarg
|
||||
n_embed = kwargs.pop("n_embed", None)
|
||||
self.hidden_size = hidden_size if n_embed is None else n_embed
|
||||
self.n_layer = n_layer
|
||||
self.n_head = n_head
|
||||
self.layer_norm_epsilon = layer_norm_epsilon
|
||||
self.initializer_range = initializer_range
|
||||
self.use_cache = use_cache
|
||||
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
||||
self.hidden_dropout = hidden_dropout
|
||||
self.attention_dropout = attention_dropout
|
||||
|
||||
self.bos_token_id = bos_token_id
|
||||
self.eos_token_id = eos_token_id
|
||||
self.multi_query = multi_query
|
||||
self.alibi = alibi
|
||||
self.bias = bias
|
||||
self.parallel_attn = parallel_attn
|
||||
|
||||
super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
|
||||
|
||||
@property
|
||||
def head_dim(self):
|
||||
return self.hidden_size // self.n_head
|
||||
|
||||
@property
|
||||
def rotary(self):
|
||||
return not self.alibi
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.30.2"
|
||||
}
|
||||
1100
modelling_RW.py
Normal file
1100
modelling_RW.py
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0952bf88966b83e080e8d80e6ab49cd8407d108e714385dea9c53b01033f115b
|
||||
size 9997558817
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ad11dcaa9617f2192b9783d9ffed3f6f184e57a6589d78659216c179426ac41
|
||||
size 3892483153
|
||||
203
pytorch_model.bin.index.json
Normal file
203
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,203 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13889971968
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
|
||||
}
|
||||
}
|
||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
">>TITLE<<",
|
||||
">>ABSTRACT<<",
|
||||
">>INTRODUCTION<<",
|
||||
">>SUMMARY<<",
|
||||
">>COMMENT<<",
|
||||
">>ANSWER<<",
|
||||
">>QUESTION<<",
|
||||
">>DOMAIN<<",
|
||||
">>PREFIX<<",
|
||||
">>SUFFIX<<",
|
||||
">>MIDDLE<<"
|
||||
],
|
||||
"eos_token": "<|endoftext|>"
|
||||
}
|
||||
176051
tokenizer.json
Normal file
176051
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
7
tokenizer_config.json
Normal file
7
tokenizer_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 2048,
|
||||
"tokenizer_class": "PreTrainedTokenizerFast"
|
||||
}
|
||||
Reference in New Issue
Block a user