初始化项目，由ModelHub XC社区提供模型
Model: nomic-ai/gpt4all-falcon Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
|
||||
116
README.md
Normal file
116
README.md
Normal file
@@ -0,0 +1,116 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- nomic-ai/gpt4all-j-prompt-generations
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Model Card for GPT4All-Falcon
|
||||
|
||||
An Apache-2 licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories.
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
This model has been finetuned from [Falcon](https://huggingface.co/tiiuae/falcon-7b)
|
||||
|
||||
- **Developed by:** [Nomic AI](https://home.nomic.ai)
|
||||
- **Model Type:** A finetuned Falcon 7B model on assistant style interaction data
|
||||
- **Language(s) (NLP):** English
|
||||
- **License:** Apache-2
|
||||
- **Finetuned from model [optional]:** [Falcon](https://huggingface.co/tiiuae/falcon-7b)
|
||||
|
||||
|
||||
To download a model with a specific revision run
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("nomic-ai/gpt4all-falcon", trust_remote_code=True)
|
||||
```
|
||||
|
||||
Downloading without specifying `revision` defaults to `main`/`v1.0`.
|
||||
|
||||
To use it for inference with Cuda, run
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, pipeline
|
||||
import transformers
|
||||
import torch
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
|
||||
model.to("cuda:0")
|
||||
|
||||
prompt = "Describe a painting of a falcon in a very detailed way." # Change this to your prompt
|
||||
prompt_template = f"### Instruction: {prompt}\n### Response:"
|
||||
|
||||
tokens = tokenizer(prompt_template, return_tensors="pt").input_ids.to("cuda:0")
|
||||
output = model.generate(input_ids=tokens, max_new_tokens=256, do_sample=True, temperature=0.8)
|
||||
|
||||
# Print the generated text
|
||||
print(tokenizer.decode(output[0]))
|
||||
```
|
||||
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [https://github.com/nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all)
|
||||
- **Base Model Repository:** [https://huggingface.co/tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b)
|
||||
- **Demo [optional]:** [https://gpt4all.io/](https://gpt4all.io/)
|
||||
|
||||
|
||||
### Training Procedure
|
||||
GPT4All is made possible by our compute partner [Paperspace](https://www.paperspace.com/).
|
||||
|
||||
Trained on a DGX cluster with 8 A100 80GB GPUs for ~12 hours. Using Deepspeed + Accelerate, we use a global batch size of 256 with a learning rate of 2e-5. More information can be found in the repo.
|
||||
|
||||
|
||||
### Results
|
||||
|
||||
Results on common sense reasoning benchmarks
|
||||
|
||||
```
|
||||
| Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. |
|
||||
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
|
||||
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
|
||||
| GPT4All-J v1.1-breezy | 74.0 | 75.1 | 63.2 | 63.6 | 55.4 | 34.9 | 38.4 | 57.8 |
|
||||
| GPT4All-J v1.2-jazzy | 74.8 | 74.9 | 63.6 | 63.8 | 56.6 | 35.3 | 41.0 | 58.6 |
|
||||
| GPT4All-J v1.3-groovy | 73.6 | 74.3 | 63.8 | 63.5 | 57.7 | 35.0 | 38.8 | 58.1 |
|
||||
| GPT4All-J Lora 6B | 68.6 | 75.8 | 66.2 | 63.5 | 56.4 | 35.7 | 40.2 | 58.1 |
|
||||
| GPT4All LLaMa Lora 7B | 73.1 | 77.6 | 72.1 | 67.8 | 51.1 | 40.4 | 40.2 | 60.3 |
|
||||
| GPT4All 13B snoozy | **83.3** | 79.2 | 75.0 | **71.3** | 60.9 | 44.2 | 43.4 | 65.3 |
|
||||
| GPT4All Falcon | 77.6 | 79.8 | 74.9 | 70.1 | 67.9 | 43.4 | 42.6 | 65.2 |
|
||||
| Dolly 6B | 68.8 | 77.3 | 67.6 | 63.9 | 62.9 | 38.7 | 41.2 | 60.1 |
|
||||
| Dolly 12B | 56.7 | 75.4 | 71.0 | 62.2 | 64.6 | 38.5 | 40.4 | 58.4 |
|
||||
| Alpaca 7B | 73.9 | 77.2 | 73.9 | 66.1 | 59.8 | 43.3 | 43.4 | 62.4 |
|
||||
| Alpaca Lora 7B | 74.3 | 79.3 | 74.0 | 68.8 | 56.6 | 43.9 | 42.6 | 62.8 |
|
||||
| GPT-J 6.7B | 65.4 | 76.2 | 66.2 | 64.1 | 62.2 | 36.6 | 38.2 | 58.4 |
|
||||
| LLama 7B | 73.1 | 77.4 | 73.0 | 66.9 | 52.5 | 41.4 | 42.4 | 61.0 |
|
||||
| LLama 13B | 68.5 | 79.1 | 76.2 | 70.1 | 60.0 | **44.6** | 42.2 | 63.0 |
|
||||
| Pythia 6.7B | 63.5 | 76.3 | 64.0 | 61.1 | 61.3 | 35.2 | 37.2 | 57.0 |
|
||||
| Pythia 12B | 67.7 | 76.6 | 67.3 | 63.8 | 63.9 | 34.8 | 38 | 58.9 |
|
||||
| Fastchat T5 | 81.5 | 64.6 | 46.3 | 61.8 | 49.3 | 33.3 | 39.4 | 53.7 |
|
||||
| Fastchat Vicuña 7B | 76.6 | 77.2 | 70.7 | 67.3 | 53.5 | 41.2 | 40.8 | 61.0 |
|
||||
| Fastchat Vicuña 13B | 81.5 | 76.8 | 73.3 | 66.7 | 57.4 | 42.7 | 43.6 | 63.1 |
|
||||
| StableVicuña RLHF | 82.3 | 78.6 | 74.1 | 70.9 | 61.0 | 43.5 | **44.4** | 65.0 |
|
||||
| StableLM Tuned | 62.5 | 71.2 | 53.6 | 54.8 | 52.4 | 31.1 | 33.4 | 51.3 |
|
||||
| StableLM Base | 60.1 | 67.4 | 41.2 | 50.1 | 44.9 | 27.0 | 32.0 | 42.2 |
|
||||
| Koala 13B | 76.5 | 77.9 | 72.6 | 68.8 | 54.3 | 41.0 | 42.8 | 62.0 |
|
||||
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
|
||||
| Mosaic MPT7B | 74.8 | 79.3 | 76.3 | 68.6 | 70.0 | 42.2 | 42.6 | 64.8 |
|
||||
| Mosaic mpt-instruct | 74.3 | 80.4 | **77.2** | 67.8 | **72.2** | **44.6** | 43.0 | **65.6** |
|
||||
| Mosaic mpt-chat | 77.1 | 78.2 | 74.5 | 67.5 | 69.4 | 43.3 | 44.2 | 64.9 |
|
||||
| Wizard 7B | 78.4 | 77.2 | 69.9 | 66.5 | 56.8 | 40.5 | 42.6 | 61.7 |
|
||||
| Wizard 7B Uncensored | 77.7 | 74.2 | 68.0 | 65.2 | 53.5 | 38.7 | 41.6 | 59.8 |
|
||||
| Wizard 13B Uncensored | 78.4 | 75.5 | 72.1 | 69.5 | 57.5 | 40.4 | 44.0 | 62.5 |
|
||||
| GPT4-x-Vicuna-13b | 81.3 | 75.0 | 75.2 | 65.0 | 58.7 | 43.9 | 43.6 | 62.2 |
|
||||
| Falcon 7b | 73.6 | **80.7** | 76.3 | 67.3 | 71.0 | 43.3 | 44.4 | 65.2 |
|
||||
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
|
||||
```
|
||||
33
config.json
Normal file
33
config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_name_or_path": "tiiuae/falcon-7b",
|
||||
"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": "4.28.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 65024
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
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": "4.28.1"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39c037a0718d9d1df673604ac661341dcc6af24ee469ca025e33333f386c0081
|
||||
size 9950994832
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98a2a82f28b94cb9921806bbdf4656ac84e3baf8ac23b7376686df72f8b529e4
|
||||
size 4483408144
|
||||
203
model.safetensors.index.json
Normal file
203
model.safetensors.index.json
Normal file
@@ -0,0 +1,203 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14434379520
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.24.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.25.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.26.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.27.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.27.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.28.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.28.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.29.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.29.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.30.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.30.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.31.self_attention.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.31.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
|
||||
"transformer.ln_f.bias": "model-00002-of-00002.safetensors",
|
||||
"transformer.ln_f.weight": "model-00002-of-00002.safetensors",
|
||||
"transformer.word_embeddings.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
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 sha256:210ef37deaf7326c7fc34fb5be68792269c3f5dac76d7dfae3415e74194bfed3
|
||||
size 13843461074
|
||||
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 sha256:59c4d3bfd6b97627ff4d0bf59ee8c5b8b9f304fbfd61bc6d405fe0d617fa2e7d
|
||||
size 13843449746
|
||||
203
pytorch_model.bin.index.json
Normal file
203
pytorch_model.bin.index.json
Normal 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"
|
||||
}
|
||||
}
|
||||
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|>"
|
||||
}
|
||||
129971
tokenizer.json
Normal file
129971
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