初始化项目，由ModelHub XC社区提供模型
Model: nigeLbasa/tadiwa-phi35-mini 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
|
||||||
201
README.md
Normal file
201
README.md
Normal file
@@ -0,0 +1,201 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- trl
|
||||||
|
- sft
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Model ID
|
||||||
|
|
||||||
|
<!-- Provide a quick summary of what the model is/does. -->
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Details
|
||||||
|
|
||||||
|
### Model Description
|
||||||
|
|
||||||
|
<!-- Provide a longer summary of what this model is. -->
|
||||||
|
|
||||||
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
||||||
|
|
||||||
|
- **Developed by:** [More Information Needed]
|
||||||
|
- **Funded by [optional]:** [More Information Needed]
|
||||||
|
- **Shared by [optional]:** [More Information Needed]
|
||||||
|
- **Model type:** [More Information Needed]
|
||||||
|
- **Language(s) (NLP):** [More Information Needed]
|
||||||
|
- **License:** [More Information Needed]
|
||||||
|
- **Finetuned from model [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
### Model Sources [optional]
|
||||||
|
|
||||||
|
<!-- Provide the basic links for the model. -->
|
||||||
|
|
||||||
|
- **Repository:** [More Information Needed]
|
||||||
|
- **Paper [optional]:** [More Information Needed]
|
||||||
|
- **Demo [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
## Uses
|
||||||
|
|
||||||
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||||
|
|
||||||
|
### Direct Use
|
||||||
|
|
||||||
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Downstream Use [optional]
|
||||||
|
|
||||||
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Out-of-Scope Use
|
||||||
|
|
||||||
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Bias, Risks, and Limitations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Recommendations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||||
|
|
||||||
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||||
|
|
||||||
|
## How to Get Started with the Model
|
||||||
|
|
||||||
|
Use the code below to get started with the model.
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
### Training Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Training Procedure
|
||||||
|
|
||||||
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||||
|
|
||||||
|
#### Preprocessing [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
|
||||||
|
#### Training Hyperparameters
|
||||||
|
|
||||||
|
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||||
|
|
||||||
|
#### Speeds, Sizes, Times [optional]
|
||||||
|
|
||||||
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
|
||||||
|
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||||
|
|
||||||
|
### Testing Data, Factors & Metrics
|
||||||
|
|
||||||
|
#### Testing Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card if possible. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Factors
|
||||||
|
|
||||||
|
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Metrics
|
||||||
|
|
||||||
|
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Results
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Summary
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Examination [optional]
|
||||||
|
|
||||||
|
<!-- Relevant interpretability work for the model goes here -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Environmental Impact
|
||||||
|
|
||||||
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||||
|
|
||||||
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||||
|
|
||||||
|
- **Hardware Type:** [More Information Needed]
|
||||||
|
- **Hours used:** [More Information Needed]
|
||||||
|
- **Cloud Provider:** [More Information Needed]
|
||||||
|
- **Compute Region:** [More Information Needed]
|
||||||
|
- **Carbon Emitted:** [More Information Needed]
|
||||||
|
|
||||||
|
## Technical Specifications [optional]
|
||||||
|
|
||||||
|
### Model Architecture and Objective
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Compute Infrastructure
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Hardware
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Software
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Citation [optional]
|
||||||
|
|
||||||
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||||
|
|
||||||
|
**BibTeX:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
**APA:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Glossary [optional]
|
||||||
|
|
||||||
|
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## More Information [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Authors [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Contact
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
8
chat_template.jinja
Normal file
8
chat_template.jinja
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>
|
||||||
|
' + message['content'] + '<|end|>
|
||||||
|
'}}{% elif message['role'] == 'user' %}{{'<|user|>
|
||||||
|
' + message['content'] + '<|end|>
|
||||||
|
'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
|
||||||
|
' + message['content'] + '<|end|>
|
||||||
|
'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
|
||||||
|
' }}{% else %}{{ eos_token }}{% endif %}
|
||||||
140
config.json
Normal file
140
config.json
Normal file
@@ -0,0 +1,140 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Phi3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"auto_map": {
|
||||||
|
"AutoConfig": "configuration_phi3.Phi3Config",
|
||||||
|
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
||||||
|
},
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"embd_pdrop": 0.0,
|
||||||
|
"eos_token_id": 32000,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3072,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8192,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"model_type": "phi3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 32,
|
||||||
|
"original_max_position_embeddings": 4096,
|
||||||
|
"pad_token_id": 32000,
|
||||||
|
"resid_pdrop": 0.0,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_parameters": {
|
||||||
|
"long_factor": [
|
||||||
|
1.0800000429153442,
|
||||||
|
1.1100000143051147,
|
||||||
|
1.1399999856948853,
|
||||||
|
1.340000033378601,
|
||||||
|
1.5899999141693115,
|
||||||
|
1.600000023841858,
|
||||||
|
1.6200000047683716,
|
||||||
|
2.620000123977661,
|
||||||
|
3.2300000190734863,
|
||||||
|
3.2300000190734863,
|
||||||
|
4.789999961853027,
|
||||||
|
7.400000095367432,
|
||||||
|
7.700000286102295,
|
||||||
|
9.09000015258789,
|
||||||
|
12.199999809265137,
|
||||||
|
17.670000076293945,
|
||||||
|
24.46000099182129,
|
||||||
|
28.57000160217285,
|
||||||
|
30.420001983642578,
|
||||||
|
30.840002059936523,
|
||||||
|
32.590003967285156,
|
||||||
|
32.93000411987305,
|
||||||
|
42.320003509521484,
|
||||||
|
44.96000289916992,
|
||||||
|
50.340003967285156,
|
||||||
|
50.45000457763672,
|
||||||
|
57.55000305175781,
|
||||||
|
57.93000411987305,
|
||||||
|
58.21000289916992,
|
||||||
|
60.1400032043457,
|
||||||
|
62.61000442504883,
|
||||||
|
62.62000274658203,
|
||||||
|
62.71000289916992,
|
||||||
|
63.1400032043457,
|
||||||
|
63.1400032043457,
|
||||||
|
63.77000427246094,
|
||||||
|
63.93000411987305,
|
||||||
|
63.96000289916992,
|
||||||
|
63.970001220703125,
|
||||||
|
64.02999877929688,
|
||||||
|
64.06999969482422,
|
||||||
|
64.08000183105469,
|
||||||
|
64.12000274658203,
|
||||||
|
64.41000366210938,
|
||||||
|
64.4800033569336,
|
||||||
|
64.51000213623047,
|
||||||
|
64.52999877929688,
|
||||||
|
64.83999633789062
|
||||||
|
],
|
||||||
|
"original_max_position_embeddings": 4096,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"rope_type": "longrope",
|
||||||
|
"short_factor": [
|
||||||
|
1.0,
|
||||||
|
1.0199999809265137,
|
||||||
|
1.0299999713897705,
|
||||||
|
1.0299999713897705,
|
||||||
|
1.0499999523162842,
|
||||||
|
1.0499999523162842,
|
||||||
|
1.0499999523162842,
|
||||||
|
1.0499999523162842,
|
||||||
|
1.0499999523162842,
|
||||||
|
1.0699999332427979,
|
||||||
|
1.0999999046325684,
|
||||||
|
1.1099998950958252,
|
||||||
|
1.1599998474121094,
|
||||||
|
1.1599998474121094,
|
||||||
|
1.1699998378753662,
|
||||||
|
1.2899998426437378,
|
||||||
|
1.339999794960022,
|
||||||
|
1.679999828338623,
|
||||||
|
1.7899998426437378,
|
||||||
|
1.8199998140335083,
|
||||||
|
1.8499997854232788,
|
||||||
|
1.8799997568130493,
|
||||||
|
1.9099997282028198,
|
||||||
|
1.9399996995925903,
|
||||||
|
1.9899996519088745,
|
||||||
|
2.0199997425079346,
|
||||||
|
2.0199997425079346,
|
||||||
|
2.0199997425079346,
|
||||||
|
2.0199997425079346,
|
||||||
|
2.0199997425079346,
|
||||||
|
2.0199997425079346,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0299997329711914,
|
||||||
|
2.0799996852874756,
|
||||||
|
2.0899996757507324,
|
||||||
|
2.189999580383301,
|
||||||
|
2.2199995517730713,
|
||||||
|
2.5899994373321533,
|
||||||
|
2.729999542236328,
|
||||||
|
2.749999523162842,
|
||||||
|
2.8399994373321533
|
||||||
|
],
|
||||||
|
"type": "longrope"
|
||||||
|
},
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"sliding_window": 262144,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "5.0.0",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32064
|
||||||
|
}
|
||||||
227
configuration_phi3.py
Normal file
227
configuration_phi3.py
Normal file
@@ -0,0 +1,227 @@
|
|||||||
|
# coding=utf-8
|
||||||
|
# Copyright 2024 Microsoft and the 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.
|
||||||
|
|
||||||
|
""" Phi-3 model configuration"""
|
||||||
|
|
||||||
|
|
||||||
|
from transformers.configuration_utils import PretrainedConfig
|
||||||
|
from transformers.utils import logging
|
||||||
|
|
||||||
|
|
||||||
|
logger = logging.get_logger(__name__)
|
||||||
|
|
||||||
|
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
||||||
|
"microsoft/Phi-3-mini-4k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json",
|
||||||
|
"microsoft/Phi-3-mini-128k-instruct": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json",
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
class Phi3Config(PretrainedConfig):
|
||||||
|
r"""
|
||||||
|
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
||||||
|
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
||||||
|
defaults will yield a similar configuration to that of the
|
||||||
|
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
||||||
|
|
||||||
|
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
||||||
|
documentation from [`PretrainedConfig`] for more information.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
vocab_size (`int`, *optional*, defaults to 32064):
|
||||||
|
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
||||||
|
`inputs_ids` passed when calling [`Phi3Model`].
|
||||||
|
hidden_size (`int`, *optional*, defaults to 3072):
|
||||||
|
Dimension of the hidden representations.
|
||||||
|
intermediate_size (`int`, *optional*, defaults to 8192):
|
||||||
|
Dimension of the MLP representations.
|
||||||
|
num_hidden_layers (`int`, *optional*, defaults to 32):
|
||||||
|
Number of hidden layers in the Transformer decoder.
|
||||||
|
num_attention_heads (`int`, *optional*, defaults to 32):
|
||||||
|
Number of attention heads for each attention layer in the Transformer decoder.
|
||||||
|
num_key_value_heads (`int`, *optional*):
|
||||||
|
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
||||||
|
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
||||||
|
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
||||||
|
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
||||||
|
by meanpooling all the original heads within that group. For more details checkout [this
|
||||||
|
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
||||||
|
`num_attention_heads`.
|
||||||
|
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
||||||
|
Dropout probability for mlp outputs.
|
||||||
|
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
||||||
|
The dropout ratio for the embeddings.
|
||||||
|
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||||||
|
The dropout ratio after computing the attention scores.
|
||||||
|
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
||||||
|
The non-linear activation function (function or string) in the decoder.
|
||||||
|
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
||||||
|
The maximum sequence length that this model might ever be used with.
|
||||||
|
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
||||||
|
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
||||||
|
original RoPE embeddings when using long scaling.
|
||||||
|
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||||
|
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||||
|
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
||||||
|
The epsilon value used for the RMSNorm.
|
||||||
|
use_cache (`bool`, *optional*, defaults to `True`):
|
||||||
|
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
||||||
|
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
||||||
|
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
||||||
|
Whether to tie weight embeddings
|
||||||
|
rope_theta (`float`, *optional*, defaults to 10000.0):
|
||||||
|
The base period of the RoPE embeddings.
|
||||||
|
rope_scaling (`dict`, *optional*):
|
||||||
|
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
||||||
|
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be `longrope` and
|
||||||
|
the `short_factor` and `long_factor` must be lists of numbers with the same length as the hidden size
|
||||||
|
divided by the number of attention heads divided by 2.
|
||||||
|
bos_token_id (`int`, *optional*, defaults to 1):
|
||||||
|
The id of the "beginning-of-sequence" token.
|
||||||
|
eos_token_id (`int`, *optional*, defaults to 32000):
|
||||||
|
The id of the "end-of-sequence" token.
|
||||||
|
pad_token_id (`int`, *optional*, defaults to 32000):
|
||||||
|
The id of the padding token.
|
||||||
|
sliding_window (`int`, *optional*):
|
||||||
|
Sliding window attention window size. If `None`, no sliding window is applied.
|
||||||
|
|
||||||
|
Example:
|
||||||
|
|
||||||
|
```python
|
||||||
|
>>> from transformers import Phi3Model, Phi3Config
|
||||||
|
|
||||||
|
>>> # Initializing a Phi-3 style configuration
|
||||||
|
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
||||||
|
|
||||||
|
>>> # Initializing a model from the configuration
|
||||||
|
>>> model = Phi3Model(configuration)
|
||||||
|
|
||||||
|
>>> # Accessing the model configuration
|
||||||
|
>>> configuration = model.config
|
||||||
|
```"""
|
||||||
|
|
||||||
|
model_type = "phi3"
|
||||||
|
keys_to_ignore_at_inference = ["past_key_values"]
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
vocab_size=32064,
|
||||||
|
hidden_size=3072,
|
||||||
|
intermediate_size=8192,
|
||||||
|
num_hidden_layers=32,
|
||||||
|
num_attention_heads=32,
|
||||||
|
num_key_value_heads=None,
|
||||||
|
resid_pdrop=0.0,
|
||||||
|
embd_pdrop=0.0,
|
||||||
|
attention_dropout=0.0,
|
||||||
|
hidden_act="silu",
|
||||||
|
max_position_embeddings=4096,
|
||||||
|
original_max_position_embeddings=4096,
|
||||||
|
initializer_range=0.02,
|
||||||
|
rms_norm_eps=1e-5,
|
||||||
|
use_cache=True,
|
||||||
|
tie_word_embeddings=False,
|
||||||
|
rope_theta=10000.0,
|
||||||
|
rope_scaling=None,
|
||||||
|
bos_token_id=1,
|
||||||
|
eos_token_id=32000,
|
||||||
|
pad_token_id=32000,
|
||||||
|
sliding_window=None,
|
||||||
|
**kwargs,
|
||||||
|
):
|
||||||
|
self.vocab_size = vocab_size
|
||||||
|
self.hidden_size = hidden_size
|
||||||
|
self.intermediate_size = intermediate_size
|
||||||
|
self.num_hidden_layers = num_hidden_layers
|
||||||
|
self.num_attention_heads = num_attention_heads
|
||||||
|
|
||||||
|
if num_key_value_heads is None:
|
||||||
|
num_key_value_heads = num_attention_heads
|
||||||
|
|
||||||
|
self.num_key_value_heads = num_key_value_heads
|
||||||
|
self.resid_pdrop = resid_pdrop
|
||||||
|
self.embd_pdrop = embd_pdrop
|
||||||
|
self.attention_dropout = attention_dropout
|
||||||
|
self.hidden_act = hidden_act
|
||||||
|
self.max_position_embeddings = max_position_embeddings
|
||||||
|
self.original_max_position_embeddings = original_max_position_embeddings
|
||||||
|
self.initializer_range = initializer_range
|
||||||
|
self.rms_norm_eps = rms_norm_eps
|
||||||
|
self.use_cache = use_cache
|
||||||
|
self.rope_theta = rope_theta
|
||||||
|
self.rope_scaling = rope_scaling
|
||||||
|
self._rope_scaling_adjustment()
|
||||||
|
self._rope_scaling_validation()
|
||||||
|
self.sliding_window = sliding_window
|
||||||
|
|
||||||
|
super().__init__(
|
||||||
|
bos_token_id=bos_token_id,
|
||||||
|
eos_token_id=eos_token_id,
|
||||||
|
pad_token_id=pad_token_id,
|
||||||
|
tie_word_embeddings=tie_word_embeddings,
|
||||||
|
**kwargs,
|
||||||
|
)
|
||||||
|
|
||||||
|
def _rope_scaling_adjustment(self):
|
||||||
|
"""
|
||||||
|
Adjust the `type` of the `rope_scaling` configuration for backward compatibility.
|
||||||
|
"""
|
||||||
|
if self.rope_scaling is None:
|
||||||
|
return
|
||||||
|
|
||||||
|
rope_scaling_type = self.rope_scaling.get("type", None)
|
||||||
|
|
||||||
|
# For backward compatibility if previous version used "su" or "yarn"
|
||||||
|
if rope_scaling_type is not None and rope_scaling_type in ["su", "yarn"]:
|
||||||
|
self.rope_scaling["type"] = "longrope"
|
||||||
|
|
||||||
|
def _rope_scaling_validation(self):
|
||||||
|
"""
|
||||||
|
Validate the `rope_scaling` configuration.
|
||||||
|
"""
|
||||||
|
if self.rope_scaling is None:
|
||||||
|
return
|
||||||
|
|
||||||
|
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 3:
|
||||||
|
raise ValueError(
|
||||||
|
"`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, "
|
||||||
|
f"got {self.rope_scaling}"
|
||||||
|
)
|
||||||
|
rope_scaling_type = self.rope_scaling.get("type", None)
|
||||||
|
rope_scaling_short_factor = self.rope_scaling.get("short_factor", None)
|
||||||
|
rope_scaling_long_factor = self.rope_scaling.get("long_factor", None)
|
||||||
|
if rope_scaling_type is None or rope_scaling_type not in ["longrope"]:
|
||||||
|
raise ValueError(f"`rope_scaling`'s type field must be one of ['longrope'], got {rope_scaling_type}")
|
||||||
|
if not (
|
||||||
|
isinstance(rope_scaling_short_factor, list)
|
||||||
|
and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor)
|
||||||
|
):
|
||||||
|
raise ValueError(
|
||||||
|
f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}"
|
||||||
|
)
|
||||||
|
if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2:
|
||||||
|
raise ValueError(
|
||||||
|
f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}"
|
||||||
|
)
|
||||||
|
if not (
|
||||||
|
isinstance(rope_scaling_long_factor, list)
|
||||||
|
and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor)
|
||||||
|
):
|
||||||
|
raise ValueError(
|
||||||
|
f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}"
|
||||||
|
)
|
||||||
|
if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2:
|
||||||
|
raise ValueError(
|
||||||
|
f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}"
|
||||||
|
)
|
||||||
11
generation_config.json
Normal file
11
generation_config.json
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": [
|
||||||
|
32007,
|
||||||
|
32001,
|
||||||
|
32000
|
||||||
|
],
|
||||||
|
"pad_token_id": 32000,
|
||||||
|
"transformers_version": "5.0.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:61117414935a25014e2dd5eb89c2ac460055fbba60db9b18fff962422d76150b
|
||||||
|
size 7642181896
|
||||||
1570
modeling_phi3.py
Normal file
1570
modeling_phi3.py
Normal file
File diff suppressed because it is too large
Load Diff
277210
tokenizer.json
Normal file
277210
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
|||||||
|
{
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"is_local": false,
|
||||||
|
"legacy": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"tokenizer_class": "TokenizersBackend",
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"use_default_system_prompt": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user