h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-07 14:32:22 +08:00
commit 4caf13cdd8
14 changed files with 131811 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.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
*.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

211
README.md Normal file
View File

@@ -0,0 +1,211 @@
---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
- h2o-llmstudio
inference: false
thumbnail: >-
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
datasets:
- OpenAssistant/oasst1
pipeline_tag: conversational
---
# Model Card
## Summary
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
- Base model: [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b)
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28)
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate`, `torch` and `einops` libraries installed.
```bash
pip install transformers==4.29.2
pip install accelerate==0.19.0
pip install torch==2.0.0
pip install einops==0.6.1
```
```python
import torch
from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
use_fast=False,
padding_side="left",
trust_remote_code=True,
)
generate_text = pipeline(
model="h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
tokenizer=tokenizer,
torch_dtype=torch.float16,
trust_remote_code=True,
use_fast=False,
device_map={"": "cuda:0"},
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?<|endoftext|><|answer|>
```
Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
```python
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
use_fast=False,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2",
torch_dtype=torch.float16,
device_map={"": "cuda:0"},
trust_remote_code=True,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2" # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?<|endoftext|><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=False,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map={"": "cuda:0"},
trust_remote_code=True,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
**inputs,
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
```
## Model Architecture
```
RWForCausalLM(
(transformer): RWModel(
(word_embeddings): Embedding(65024, 4544)
(h): ModuleList(
(0-31): 32 x DecoderLayer(
(input_layernorm): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
(self_attention): Attention(
(maybe_rotary): RotaryEmbedding()
(query_key_value): Linear(in_features=4544, out_features=4672, bias=False)
(dense): Linear(in_features=4544, out_features=4544, bias=False)
(attention_dropout): Dropout(p=0.0, inplace=False)
)
(mlp): MLP(
(dense_h_to_4h): Linear(in_features=4544, out_features=18176, bias=False)
(act): GELU(approximate='none')
(dense_4h_to_h): Linear(in_features=18176, out_features=4544, bias=False)
)
)
)
(ln_f): LayerNorm((4544,), eps=1e-05, elementwise_affine=True)
)
(lm_head): Linear(in_features=4544, out_features=65024, bias=False)
)
```
## Model Configuration
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
## Model Validation
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
```bash
CUDA_VISIBLE_DEVICES=0 python main.py --model hf-causal-experimental --model_args pretrained=h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 --tasks openbookqa,arc_easy,winogrande,hellaswag,arc_challenge,piqa,boolq --device cuda &> eval.log
```
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.

93
cfg.yaml Normal file
View File

@@ -0,0 +1,93 @@
architecture:
backbone_dtype: float16
force_embedding_gradients: false
gradient_checkpointing: true
intermediate_dropout: 0.0
pretrained: true
pretrained_weights: ''
augmentation:
random_parent_probability: 0.0
skip_parent_probability: 0.0
token_mask_probability: 0.0
dataset:
add_eos_token_to_answer: true
add_eos_token_to_prompt: true
answer_column: output
data_sample: 1.0
data_sample_choice:
- Train
- Validation
mask_prompt_labels: true
parent_id_column: parent_id
prompt_column:
- instruction
text_answer_separator: <|answer|>
text_prompt_start: <|prompt|>
train_dataframe: data/user/oasst/train_full_allrank.pq
validation_dataframe: data/user/oasst/val.csv
validation_size: 0.01
validation_strategy: custom
environment:
compile_model: false
find_unused_parameters: false
gpus:
- '0'
- '1'
- '2'
mixed_precision: true
number_of_workers: 8
seed: -1
trust_remote_code: true
use_fsdp: false
experiment_name: h2ogpt-gm-oasst1-en-2048-falcon-7b-v2
llm_backbone: tiiuae/falcon-7b
logging:
logger: Neptune
neptune_project: Zoo/h2o-llm
number_of_texts: 10
output_directory: output/user/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2/
prediction:
batch_size_inference: 0
do_sample: false
max_length_inference: 1024
metric: GPT3.5
min_length_inference: 2
num_beams: 1
num_history: 2
repetition_penalty: 1.2
stop_tokens: ''
temperature: 0.3
top_k: 0
top_p: 1.0
problem_type: text_causal_language_modeling
tokenizer:
add_prefix_space: false
add_prompt_answer_tokens: false
max_length: 2048
max_length_answer: 1024
max_length_prompt: 2048
padding_quantile: 1.0
use_fast: false
training:
batch_size: 3
differential_learning_rate: 1.0e-05
differential_learning_rate_layers: []
drop_last_batch: true
epochs: 1
evaluate_before_training: false
evaluation_epochs: 0.5
grad_accumulation: 1
gradient_clip: 0.0
learning_rate: 0.0001
lora: true
lora_alpha: 32
lora_dropout: 0.05
lora_r: 16
lora_target_modules: query_key_value,dense_h_to_4h,dense_4h_to_h,dense
loss_function: CrossEntropy
optimizer: AdamW
save_best_checkpoint: false
schedule: Cosine
train_validation_data: false
warmup_epochs: 0.0
weight_decay: 0.0

40
config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"attention_probs_dropout_prob": 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,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_dropout_prob": 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": "float16",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 65024
}

79
configuration_RW.py Normal file
View 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
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 11,
"eos_token_id": 11,
"transformers_version": "4.29.2"
}

42
h2oai_pipeline.py Normal file
View File

@@ -0,0 +1,42 @@
from transformers import TextGenerationPipeline
from transformers.pipelines.text_generation import ReturnType
STYLE = "<|prompt|>{instruction}<|endoftext|><|answer|>"
class H2OTextGenerationPipeline(TextGenerationPipeline):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.prompt = STYLE
def preprocess(
self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs
):
prompt_text = self.prompt.format(instruction=prompt_text)
return super().preprocess(
prompt_text,
prefix=prefix,
handle_long_generation=handle_long_generation,
**generate_kwargs,
)
def postprocess(
self,
model_outputs,
return_type=ReturnType.FULL_TEXT,
clean_up_tokenization_spaces=True,
):
records = super().postprocess(
model_outputs,
return_type=return_type,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
)
for rec in records:
rec["generated_text"] = (
rec["generated_text"]
.split("<|answer|>")[1]
.strip()
.split("<|prompt|>")[0]
.strip()
)
return records

1100
modelling_RW.py Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model-00001-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a877d0a22abff11b72b5c247b43a7e5985deea479b09403d11ce216799c86ed
size 9951026273

3
pytorch_model-00002-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09eae470105b2b89f42acbd1ba0fa31e8d503df1b018b3507f0bed5050bd8032
size 4483420827

203
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,203 @@
{
"metadata": {
"total_size": 14434379520
},
"weight_map": {
"lm_head.weight": "pytorch_model-00002-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"
}
}

19
special_tokens_map.json Normal file
View File

@@ -0,0 +1,19 @@
{
"additional_special_tokens": [
">>TITLE<<",
">>ABSTRACT<<",
">>INTRODUCTION<<",
">>SUMMARY<<",
">>COMMENT<<",
">>ANSWER<<",
">>QUESTION<<",
">>DOMAIN<<",
">>PREFIX<<",
">>SUFFIX<<",
">>MIDDLE<<"
],
"cls_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"sep_token": "<|endoftext|>"
}

129971
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

7
tokenizer_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"add_prefix_space": false,
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 2048,
"tokenizer_class": "PreTrainedTokenizerFast"
}