初始化项目，由ModelHub XC社区提供模型
Model: DeepGlint-AI/UniME-Phi3.5-V-4.2B Source: Original Platform
This commit is contained in:
ModelHub XC
41
.gitattributes
vendored
Normal file
41
.gitattributes
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
*.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
|
||||
figures/fig1.png filter=lfs diff=lfs merge=lfs -text
|
||||
figures/fig2.png filter=lfs diff=lfs merge=lfs -text
|
||||
figures/fig3.png filter=lfs diff=lfs merge=lfs -text
|
||||
figures/res1.png filter=lfs diff=lfs merge=lfs -text
|
||||
figures/res2.png filter=lfs diff=lfs merge=lfs -text
|
||||
figures/MMEB.png filter=lfs diff=lfs merge=lfs -text
|
||||
125
README.md
Normal file
125
README.md
Normal file
@@ -0,0 +1,125 @@
|
||||
---
|
||||
license: mit
|
||||
datasets:
|
||||
- TIGER-Lab/MMEB-train
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- microsoft/Phi-3.5-vision-instruct
|
||||
library_name: transformers
|
||||
tags:
|
||||
- Retrieval
|
||||
- Multimodal
|
||||
- Embedding
|
||||
pipeline_tag: image-text-to-text
|
||||
---
|
||||
|
||||
# Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
|
||||
<a href="https://github.com/GaryGuTC">Tiancheng Gu*</a>,</span>
|
||||
<a href="https://kaicheng-yang0828.github.io">Kaicheng Yang*</a>,</span>
|
||||
Ziyong Feng,</span>
|
||||
Xingjun Wang,</span>
|
||||
Yanzhao Zhang,</span>
|
||||
Dingkun Long,</span>
|
||||
Yingda Chen,</span>
|
||||
<a href="https://weidong-tom-cai.github.io/">Weidong Cai</a>,</span>
|
||||
<a href="https://jiankangdeng.github.io">Jiankang Deng</a></span>
|
||||
|
||||
[🏡 Project Page](https://garygutc.github.io/UniME) | [📄 Paper](https://arxiv.org/pdf/2504.17432) | [💻 Github](https://github.com/deepglint/UniME)
|
||||
|
||||
UniME achieves the top ranking on the MMEB leaderboard training using a 336×336 image resolution.（The screenshot is captured at 08:00 UTC+8 on May 6, 2025.）
|
||||
|
||||
<p align="center">
|
||||
<img src="figures/MMEB.png">
|
||||
</p>
|
||||
|
||||
## 💡 Highlights
|
||||
<p align="center">
|
||||
<img src="figures/fig1.png">
|
||||
</p>
|
||||
|
||||
To enhance the MLLM's embedding capability, we propose textual discriminative knowledge distillation. The training process involves decoupling the MLLM's LLM component and processing text with the prompt "Summarize the above sentences in one word.", followed by aligning the student (MLLM) and teacher (NV-Embed V2) embeddings via KL divergence on batch-wise similarity distributions. **Notably, only the LLM component is fine-tuned during this process, while all other parameters remain frozen**.
|
||||
|
||||
<p align="center">
|
||||
<img src="figures/fig2.png">
|
||||
</p>
|
||||
|
||||
After that, we propose hard negative enhanced instruction tuning enhances multimodal systems by improving visual sensitivity, strengthening cross-modal alignment, and boosting instruction-following capabilities. At its core are two key innovations: a false negative filtering mechanism using a similarity threshold to eliminate misleading samples, and an automatic hard negative sampling strategy that selects top-k similar but non-matching examples to increase training difficulty.
|
||||
<p align="center">
|
||||
<img src="figures/fig3.png">
|
||||
</p>
|
||||
|
||||
|
||||
## 🧭 Quick Start
|
||||
```bash
|
||||
git clone https://github.com/deepglint/UniME.git
|
||||
cd UniME
|
||||
conda create -n uniME python=3.10 -y
|
||||
conda activate uniME
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
```python
|
||||
import torch
|
||||
from PIL import Image
|
||||
from torch.nn import functional as F
|
||||
from transformers import AutoProcessor, AutoModelForCausalLM
|
||||
|
||||
base_model_path="DeepGlint-AI/UniME-Phi3.5-V-4.2B"
|
||||
img_prompt = '<|user|>\n<|image_1|>\nSummary above image in one word: <|end|>\n<|assistant|>\n'
|
||||
text_prompt = '<|user|>\n<sent>\nSummary above sentence in one word: <|end|>\n<|assistant|>\n'
|
||||
|
||||
text = "A man is crossing the street with a red car parked nearby."
|
||||
image_path = "figures/demo.png"
|
||||
input_texts = text_prompt.replace('<sent>', text)
|
||||
input_image_prompt = img_prompt
|
||||
input_image = [Image.open(image_path)]
|
||||
|
||||
transform = AutoProcessor.from_pretrained(base_model_path, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(base_model_path,device_map="cuda", trust_remote_code=True，torch_dtype=torch.float16, _attn_implementation='flash_attention_2')
|
||||
transform.tokenizer.padding_side = "left"
|
||||
transform.tokenizer.padding = True
|
||||
|
||||
inputs_text = transform(text=input_texts,
|
||||
images=None,
|
||||
return_tensors="pt",
|
||||
padding=True)
|
||||
for key in inputs_text: inputs_text[key] = inputs_text[key].to("cuda")
|
||||
inputs_image = transform(text=input_image_prompt,
|
||||
images=input_image,
|
||||
return_tensors="pt",
|
||||
padding=True).to("cuda")
|
||||
|
||||
with torch.no_grad():
|
||||
emb_text = model(**inputs_text, output_hidden_states=True, return_dict=True).hidden_states[-1][:, -1, :]
|
||||
emb_image = model(**inputs_image, output_hidden_states=True, return_dict=True).hidden_states[-1][:, -1, :]
|
||||
emb_text = F.normalize(emb_text, dim=-1)
|
||||
emb_image = F.normalize(emb_image, dim=-1)
|
||||
Score = emb_image @ emb_text.T
|
||||
print("Score: ", Score)
|
||||
```
|
||||
|
||||
## 🔢 Results
|
||||
### Diverse Retrieval
|
||||
<p align="center">
|
||||
<img src="figures/res1.png">
|
||||
</p>
|
||||
|
||||
### MMEB
|
||||
<p align="center">
|
||||
<img src="figures/res2.png">
|
||||
</p>
|
||||
|
||||
## 📖 Citation
|
||||
If you find this repository useful, please use the following BibTeX entry for citation.
|
||||
```latex
|
||||
@misc{gu2025breakingmodalitybarrieruniversal,
|
||||
title={Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs},
|
||||
author={Tiancheng Gu and Kaicheng Yang and Ziyong Feng and Xingjun Wang and Yanzhao Zhang and Dingkun Long and Yingda Chen and Weidong Cai and Jiankang Deng},
|
||||
year={2025},
|
||||
eprint={2504.17432},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CV},
|
||||
url={https://arxiv.org/abs/2504.17432},
|
||||
}
|
||||
```
|
||||
150
config.json
Normal file
150
config.json
Normal file
@@ -0,0 +1,150 @@
|
||||
{
|
||||
"_name_or_path": "UniME_Phi35V",
|
||||
"architectures": [
|
||||
"Phi3VForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_phi3_v.Phi3VConfig",
|
||||
"AutoModelForCausalLM": "modeling_phi3_v.Phi3VForCausalLM"
|
||||
},
|
||||
"bos_token_id": 1,
|
||||
"embd_layer": {
|
||||
"embedding_cls": "image",
|
||||
"hd_transform_order": "sub_glb",
|
||||
"projection_cls": "mlp",
|
||||
"use_hd_transform": true,
|
||||
"with_learnable_separator": true
|
||||
},
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"img_processor": {
|
||||
"image_dim_out": 1024,
|
||||
"model_name": "openai/clip-vit-large-patch14-336",
|
||||
"name": "clip_vision_model",
|
||||
"num_img_tokens": 144
|
||||
},
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "phi3_v",
|
||||
"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_scaling": {
|
||||
"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
|
||||
],
|
||||
"short_factor": [
|
||||
1.08,
|
||||
1.1,
|
||||
1.1300000000000001,
|
||||
1.2800000000000002,
|
||||
1.3100000000000003,
|
||||
1.4500000000000004,
|
||||
1.4500000000000004,
|
||||
1.9500000000000008,
|
||||
2.030000000000001,
|
||||
2.4299999999999926,
|
||||
2.5699999999999896,
|
||||
2.9499999999999815,
|
||||
3.729999999999965,
|
||||
3.869999999999962,
|
||||
4.189999999999955,
|
||||
4.43999999999995,
|
||||
4.6399999999999455,
|
||||
4.979999999999938,
|
||||
5.159999999999934,
|
||||
5.279999999999932,
|
||||
5.759999999999922,
|
||||
5.889999999999919,
|
||||
5.889999999999919,
|
||||
5.969999999999917,
|
||||
6.089999999999915,
|
||||
6.2799999999999105,
|
||||
6.7699999999999,
|
||||
6.8899999999998975,
|
||||
7.109999999999893,
|
||||
7.129999999999892,
|
||||
7.179999999999891,
|
||||
7.289999999999889,
|
||||
7.339999999999888,
|
||||
7.559999999999883,
|
||||
7.619999999999882,
|
||||
7.69999999999988,
|
||||
7.879999999999876,
|
||||
7.879999999999876,
|
||||
7.879999999999876,
|
||||
7.939999999999875,
|
||||
7.949999999999875,
|
||||
7.979999999999874,
|
||||
8.19999999999987,
|
||||
8.439999999999864,
|
||||
8.469999999999864,
|
||||
8.589999999999861,
|
||||
8.809999999999857,
|
||||
8.999999999999853
|
||||
],
|
||||
"type": "su"
|
||||
},
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 262144,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.48.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32064
|
||||
}
|
||||
218
configuration_phi3_v.py
Normal file
218
configuration_phi3_v.py
Normal file
@@ -0,0 +1,218 @@
|
||||
# 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-V model configuration"""
|
||||
|
||||
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
PHI3V_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
||||
"microsoft/Phi-3-vision-128k-instruct": "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/resolve/main/config.json",
|
||||
"microsoft/Phi-3.5-vision-instruct": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct/resolve/main/config.json",
|
||||
}
|
||||
|
||||
|
||||
class Phi3VConfig(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`Phi3VModel`]. 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-vision-128k-instruct](https://huggingface.co/microsoft/Phi-3-vision-128k-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-V model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`Phi3VModel`].
|
||||
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 either `su` or `yarn` 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.
|
||||
embd_layer (`str`, *optional*, defaults to `"default"`):
|
||||
The embedding layer to use. Can be either `"default"` or `"image"`. "default" uses the standard embedding for text.
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
>>> from transformers import Phi3VModel, Phi3VConfig
|
||||
|
||||
>>> # Initializing a Phi-3-V style configuration
|
||||
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-vision-128k-instruct")
|
||||
|
||||
>>> # Initializing a model from the configuration
|
||||
>>> model = Phi3VModel(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
|
||||
model_type = "phi3_v"
|
||||
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,
|
||||
embd_layer: str = "default",
|
||||
**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_validation()
|
||||
self.sliding_window = sliding_window
|
||||
self.embd_layer = embd_layer
|
||||
|
||||
|
||||
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_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 ["su", "yarn"]:
|
||||
raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], 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)}"
|
||||
)
|
||||
3
figures/MMEB.png
Normal file
3
figures/MMEB.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4a4944b23a6f754d63af999555753837da3475b5e85fe13a85d0091addacf57
|
||||
size 300295
|
||||
BIN
figures/demo.png
Normal file
BIN
figures/demo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 92 KiB |
3
figures/fig1.png
Normal file
3
figures/fig1.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0e016694b7e1190cba7aa043c9a1bde0423b7037b1605ef6acaff265a971e7a
|
||||
size 739233
|
||||
3
figures/fig2.png
Normal file
3
figures/fig2.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c04eb78d512f51f278b7def84d8f0aa47e589151842c02fea259f7505a3c947
|
||||
size 373028
|
||||
3
figures/fig3.png
Normal file
3
figures/fig3.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d370cd5d9665ce0c62abfe53c288d652e9d848b00ce33f5cbe38185636931823
|
||||
size 746132
|
||||
3
figures/res1.png
Normal file
3
figures/res1.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9663773aac5b1bd9e265ea255ec61470cb19306dbc90bc25edac6e4b71227317
|
||||
size 202777
|
||||
3
figures/res2.png
Normal file
3
figures/res2.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7a652651d1844392feab2207b474e5bc8ece28c55ec9fdd17a24ecdc1ede399e
|
||||
size 327205
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 32000,
|
||||
"transformers_version": "4.48.0"
|
||||
}
|
||||
1942
modeling_phi3_v.py
Normal file
1942
modeling_phi3_v.py
Normal file
File diff suppressed because it is too large
Load Diff
21
preprocessor_config.json
Normal file
21
preprocessor_config.json
Normal file
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"auto_map": {
|
||||
"AutoImageProcessor": "processing_phi3_v.Phi3VImageProcessor",
|
||||
"AutoProcessor": "processing_phi3_v.Phi3VProcessor"
|
||||
},
|
||||
"do_convert_rgb": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Phi3VImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"num_crops": 4,
|
||||
"num_img_tokens": 144,
|
||||
"processor_class": "Phi3VProcessor"
|
||||
}
|
||||
478
processing_phi3_v.py
Normal file
478
processing_phi3_v.py
Normal file
@@ -0,0 +1,478 @@
|
||||
# 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.
|
||||
|
||||
"""
|
||||
Processor class for Phi3-V.
|
||||
"""
|
||||
import re
|
||||
from typing import List, Optional, Union
|
||||
|
||||
import torch
|
||||
|
||||
import transformers
|
||||
from transformers.feature_extraction_utils import BatchFeature
|
||||
from transformers.image_utils import ImageInput
|
||||
from transformers.processing_utils import ProcessorMixin
|
||||
from transformers.tokenization_utils_base import PaddingStrategy, TextInput, TruncationStrategy
|
||||
from transformers.utils import TensorType
|
||||
|
||||
|
||||
"""Image processor class for Phi3-V."""
|
||||
|
||||
from typing import List, Optional, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
from transformers.image_processing_utils import BaseImageProcessor, BatchFeature
|
||||
from transformers.image_transforms import (
|
||||
convert_to_rgb,
|
||||
)
|
||||
from transformers.image_utils import (
|
||||
OPENAI_CLIP_MEAN,
|
||||
OPENAI_CLIP_STD,
|
||||
ImageInput,
|
||||
make_list_of_images,
|
||||
valid_images,
|
||||
)
|
||||
from transformers.utils import TensorType, is_vision_available, logging
|
||||
|
||||
from transformers import AutoImageProcessor
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
if is_vision_available():
|
||||
from PIL import Image
|
||||
|
||||
import torch
|
||||
import torchvision
|
||||
|
||||
def padding_336(b):
|
||||
width, height = b.size
|
||||
tar = int(np.ceil(height / 336) * 336)
|
||||
top_padding = int((tar - height)/2)
|
||||
bottom_padding = tar - height - top_padding
|
||||
left_padding = 0
|
||||
right_padding = 0
|
||||
b = torchvision.transforms.functional.pad(b, [left_padding, top_padding, right_padding, bottom_padding], fill=[255,255,255])
|
||||
|
||||
return b
|
||||
|
||||
def calc_padded_size(width, height, padding_unit=336):
|
||||
target_height = int(np.ceil(height / padding_unit) * padding_unit)
|
||||
top_padding = int((target_height - height) / 2)
|
||||
bottom_padding = target_height - height - top_padding
|
||||
left_padding = 0
|
||||
right_padding = 0
|
||||
padded_width = width + left_padding + right_padding
|
||||
padded_height = height + top_padding + bottom_padding
|
||||
return padded_width, padded_height
|
||||
|
||||
def HD_transform(img, hd_num=16):
|
||||
width, height = img.size
|
||||
trans = False
|
||||
if width < height:
|
||||
img = img.transpose(Image.TRANSPOSE)
|
||||
trans = True
|
||||
width, height = img.size
|
||||
ratio = (width/ height)
|
||||
scale = 1
|
||||
while scale*np.ceil(scale/ratio) <= hd_num:
|
||||
scale += 1
|
||||
scale -= 1
|
||||
new_w = int(scale * 336)
|
||||
new_h = int(new_w / ratio)
|
||||
|
||||
img = torchvision.transforms.functional.resize(img, [new_h, new_w],)
|
||||
img = padding_336(img)
|
||||
width, height = img.size
|
||||
if trans:
|
||||
img = img.transpose(Image.TRANSPOSE)
|
||||
|
||||
return img
|
||||
|
||||
def calc_hd_transform_size(width, height, hd_num=16):
|
||||
transposed = False
|
||||
if width < height:
|
||||
width, height = height, width
|
||||
transposed = True
|
||||
|
||||
ratio = width / height
|
||||
scale = 1
|
||||
while scale * np.ceil(scale / ratio) <= hd_num:
|
||||
scale += 1
|
||||
scale -= 1
|
||||
|
||||
new_width = int(scale * 336)
|
||||
new_height = int(new_width / ratio)
|
||||
|
||||
padded_width, padded_height = calc_padded_size(new_width, new_height)
|
||||
|
||||
if transposed:
|
||||
padded_width, padded_height = padded_height, padded_width
|
||||
|
||||
return padded_width, padded_height
|
||||
|
||||
def pad_to_max_num_crops_tensor(images, max_crops=5):
|
||||
"""
|
||||
images: B x 3 x H x W, B<=max_crops
|
||||
"""
|
||||
B, _, H, W = images.shape
|
||||
if B < max_crops:
|
||||
pad = torch.zeros(max_crops - B, 3, H, W, dtype=images.dtype, device=images.device)
|
||||
images = torch.cat([images, pad], dim=0)
|
||||
return images
|
||||
|
||||
|
||||
class Phi3VImageProcessor(BaseImageProcessor):
|
||||
r"""
|
||||
Constructs a Phi3 image processor. Based on [`CLIPImageProcessor`] with incorporation of additional techniques
|
||||
for processing high resolution images as explained in the [InternLM-XComposer2-4KHD](https://arxiv.org/pdf/2404.06512)
|
||||
|
||||
Args:
|
||||
image_mean (`float` or `List[float]`, *optional*, defaults to `[0.48145466, 0.4578275, 0.40821073]`):
|
||||
Mean to use if normalizing the image. This is a float or list of floats the length of the number of
|
||||
channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method.
|
||||
image_std (`float` or `List[float]`, *optional*, defaults to `[0.26862954, 0.26130258, 0.27577711]`):
|
||||
Standard deviation to use if normalizing the image. This is a float or list of floats the length of the
|
||||
number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method.
|
||||
Can be overridden by the `image_std` parameter in the `preprocess` method.
|
||||
do_convert_rgb (`bool`, *optional*, defaults to `True`):
|
||||
Whether to convert the image to RGB.
|
||||
"""
|
||||
|
||||
model_input_names = ["pixel_values"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
num_crops: int = 1,
|
||||
image_mean: Optional[Union[float, List[float]]] = None,
|
||||
image_std: Optional[Union[float, List[float]]] = None,
|
||||
do_convert_rgb: bool = True,
|
||||
**kwargs,
|
||||
) -> None:
|
||||
super().__init__(**kwargs)
|
||||
self.num_crops = num_crops
|
||||
self.image_mean = image_mean if image_mean is not None else OPENAI_CLIP_MEAN
|
||||
self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD
|
||||
self.do_convert_rgb = do_convert_rgb
|
||||
|
||||
def calc_num_image_tokens(
|
||||
self,
|
||||
images: ImageInput
|
||||
):
|
||||
""" Calculate the number of image tokens for each image.
|
||||
Args:
|
||||
images (`ImageInput`):
|
||||
Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
|
||||
passing in images with pixel values between 0 and 1, set `do_rescale=False`.
|
||||
"""
|
||||
images = make_list_of_images(images)
|
||||
|
||||
if not valid_images(images):
|
||||
raise ValueError(
|
||||
"Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
|
||||
"torch.Tensor, tf.Tensor or jax.ndarray."
|
||||
)
|
||||
|
||||
images = [image.convert('RGB') for image in images]
|
||||
# (H, W, C)
|
||||
elems = [HD_transform(im, hd_num = self.num_crops) for im in images]
|
||||
shapes = [[im.size[1], im.size[0]] for im in elems]
|
||||
num_img_tokens = [int((h//336*w//336+1)*144 + 1 + (h//336+1)*12) for h, w in shapes]
|
||||
return num_img_tokens
|
||||
|
||||
def calc_num_image_tokens_from_image_size(self, width, height):
|
||||
"""
|
||||
Calculate the number of image tokens for a given image size.
|
||||
Args:
|
||||
width (`int`): Width of the image.
|
||||
height (`int`): Height of the image.
|
||||
"""
|
||||
new_width, new_height = calc_hd_transform_size(width, height, hd_num=self.num_crops)
|
||||
num_img_tokens = int((new_height // 336 * new_width // 336 + 1) * 144 + 1 + (new_height // 336 + 1) * 12)
|
||||
return num_img_tokens
|
||||
|
||||
def preprocess(
|
||||
self,
|
||||
images: ImageInput,
|
||||
image_mean: Optional[Union[float, List[float]]] = None,
|
||||
image_std: Optional[Union[float, List[float]]] = None,
|
||||
do_convert_rgb: bool = None,
|
||||
return_tensors: Optional[Union[str, TensorType]] = None,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
images (`ImageInput`):
|
||||
Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
|
||||
passing in images with pixel values between 0 and 1, set `do_rescale=False`.
|
||||
image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`):
|
||||
Image mean to use for normalization. Only has an effect if `do_normalize` is set to `True`.
|
||||
image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
|
||||
Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to
|
||||
`True`.
|
||||
do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
|
||||
Whether to convert the image to RGB.
|
||||
return_tensors (`str` or `TensorType`, *optional*):
|
||||
The type of tensors to return. Can be one of:
|
||||
- Unset: Return a list of `np.ndarray`.
|
||||
- `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
|
||||
- `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
|
||||
- `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
|
||||
- `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
|
||||
"""
|
||||
image_mean = image_mean if image_mean is not None else self.image_mean
|
||||
image_std = image_std if image_std is not None else self.image_std
|
||||
do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb
|
||||
|
||||
images = make_list_of_images(images)
|
||||
|
||||
if not valid_images(images):
|
||||
raise ValueError(
|
||||
"Invalid image type. Must be of type PIL.Image.Image, numpy.ndarray, "
|
||||
"torch.Tensor, tf.Tensor or jax.ndarray."
|
||||
)
|
||||
|
||||
if do_convert_rgb:
|
||||
images = [convert_to_rgb(image) for image in images]
|
||||
|
||||
image_sizes = []
|
||||
img_processor = torchvision.transforms.Compose([
|
||||
torchvision.transforms.ToTensor(),
|
||||
torchvision.transforms.Normalize(image_mean, image_std)
|
||||
])
|
||||
|
||||
# PIL images
|
||||
# HD_transform pad images to size of multiiply of 336, 336
|
||||
# convert to RGB first
|
||||
images = [image.convert('RGB') for image in images]
|
||||
elems = [HD_transform(im, hd_num = self.num_crops) for im in images]
|
||||
# tensor transform and normalize
|
||||
hd_images = [img_processor(im) for im in elems]
|
||||
# create global image
|
||||
global_image = [torch.nn.functional.interpolate(im.unsqueeze(0).float(), size=(336, 336), mode='bicubic',).to(im.dtype) for im in hd_images]
|
||||
|
||||
# [(3, h, w)], where h, w is multiple of 336
|
||||
shapes = [[im.size(1), im.size(2)] for im in hd_images]
|
||||
num_img_tokens = [int(((h//336)*(w//336)+1)*144 + 1 + (h//336+1)*12) for h, w in shapes]
|
||||
# reshape to channel dimension -> (num_images, num_crops, 3, 336, 336)
|
||||
# (1, 3, h//336, 336, w//336, 336) -> (1, h//336, w//336, 3, 336, 336) -> (h//336*w//336, 3, 336, 336)
|
||||
hd_images_reshape = [im.reshape(1, 3, h//336, 336, w//336, 336).permute(0,2,4,1,3,5).reshape(-1, 3, 336, 336).contiguous() for im, (h, w) in zip(hd_images, shapes)]
|
||||
# concat global image and local image
|
||||
hd_images_reshape = [torch.cat([_global_image] + [_im], dim=0) for _global_image, _im in zip(global_image, hd_images_reshape)]
|
||||
|
||||
# pad to max_num_crops
|
||||
image_transformed = [pad_to_max_num_crops_tensor(im, self.num_crops+1) for im in hd_images_reshape]
|
||||
image_transformed = torch.stack(image_transformed, dim=0)
|
||||
image_sizes = [torch.LongTensor(_shapes) for _shapes in shapes]
|
||||
padded_images = image_transformed
|
||||
image_sizes = shapes
|
||||
|
||||
data = {"pixel_values": padded_images,
|
||||
"image_sizes": image_sizes,
|
||||
"num_img_tokens": num_img_tokens
|
||||
}
|
||||
|
||||
return BatchFeature(data=data, tensor_type=return_tensors)
|
||||
|
||||
AutoImageProcessor.register("Phi3VImageProcessor", Phi3VImageProcessor)
|
||||
|
||||
transformers.Phi3VImageProcessor = Phi3VImageProcessor
|
||||
|
||||
class Phi3VProcessor(ProcessorMixin):
|
||||
r"""
|
||||
Constructs a Phi3-V processor which wraps a Phi3-V image processor and a LLaMa tokenizer into a single processor.
|
||||
|
||||
[`Phi3VProcessor`] offers all the functionalities of [`Phi3VImageProcessor`] and [`LlamaTokenizerFast`]. See the
|
||||
[`~Phi3VProcessor.__call__`] and [`~Phi3VProcessor.decode`] for more information.
|
||||
|
||||
Args:
|
||||
image_processor ([`Phi3VImageProcessor`], *optional*):
|
||||
The image processor is a required input.
|
||||
tokenizer ([`LlamaTokenizerFast`], *optional*):
|
||||
The tokenizer is a required input.
|
||||
"""
|
||||
|
||||
attributes = ["image_processor", "tokenizer"]
|
||||
image_processor_class = "Phi3VImageProcessor"
|
||||
tokenizer_class = ("LlamaTokenizer", "LlamaTokenizerFast")
|
||||
special_image_token = "<|image|>"
|
||||
|
||||
def __init__(self, image_processor, tokenizer):
|
||||
self.image_processor = image_processor
|
||||
self.tokenizer = tokenizer
|
||||
self.num_img_tokens = image_processor.num_img_tokens
|
||||
self.img_tokens = [f"<|image_{i+1}|>" for i in range(1000000)]
|
||||
|
||||
def __call__(
|
||||
self,
|
||||
text: Union[TextInput, List[TextInput]],
|
||||
images: ImageInput = None,
|
||||
padding: Union[bool, str, PaddingStrategy] = False,
|
||||
truncation: Union[bool, str, TruncationStrategy] = None,
|
||||
max_length=None,
|
||||
return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
|
||||
) -> BatchFeature:
|
||||
"""
|
||||
Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
|
||||
and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`] if `text` is not `None` to encode
|
||||
the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
|
||||
Phi3ImageProcessor's [`~Phi3ImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
|
||||
of the above two methods for more information.
|
||||
|
||||
Args:
|
||||
text (`str`, `List[str]`, `List[List[str]]`):
|
||||
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
|
||||
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
|
||||
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
|
||||
images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
|
||||
The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
|
||||
tensor. Both channels-first and channels-last formats are supported.
|
||||
padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
|
||||
Select a strategy to pad the returned sequences (according to the model's padding side and padding
|
||||
index) among:
|
||||
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
|
||||
sequence if provided).
|
||||
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
|
||||
acceptable input length for the model if that argument is not provided.
|
||||
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
|
||||
lengths).
|
||||
max_length (`int`, *optional*):
|
||||
Maximum length of the returned list and optionally padding length (see above).
|
||||
truncation (`bool`, *optional*):
|
||||
Activates truncation to cut input sequences longer than `max_length` to `max_length`.
|
||||
return_tensors (`str` or [`~utils.TensorType`], *optional*):
|
||||
If set, will return tensors of a particular framework. Acceptable values are:
|
||||
|
||||
- `'tf'`: Return TensorFlow `tf.constant` objects.
|
||||
- `'pt'`: Return PyTorch `torch.Tensor` objects.
|
||||
- `'np'`: Return NumPy `np.ndarray` objects.
|
||||
- `'jax'`: Return JAX `jnp.ndarray` objects.
|
||||
|
||||
Returns:
|
||||
[`BatchFeature`]: A [`BatchFeature`] with the following fields:
|
||||
|
||||
- **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
|
||||
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
|
||||
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
|
||||
`None`).
|
||||
- **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
|
||||
"""
|
||||
if images is not None:
|
||||
image_inputs = self.image_processor(images, return_tensors=return_tensors)
|
||||
else:
|
||||
image_inputs = {}
|
||||
inputs = self._convert_images_texts_to_inputs(image_inputs, text, padding=padding, truncation=truncation, max_length=max_length, return_tensors=return_tensors)
|
||||
return inputs
|
||||
|
||||
def calc_num_image_tokens(self, images: ImageInput):
|
||||
""" Calculate the number of image tokens for each image.
|
||||
Args:
|
||||
images (`ImageInput`):
|
||||
Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
|
||||
passing in images with pixel values between 0 and 1, set `do_rescale=False`.
|
||||
"""
|
||||
return self.image_processor.calc_num_image_tokens(images)
|
||||
|
||||
def calc_num_image_tokens_from_image_size(self, width, height):
|
||||
""" Calculate the number of image token for an image with given width and height.
|
||||
Args:
|
||||
width (`int`):
|
||||
Width of the image.
|
||||
height (`int`):
|
||||
Height of the image.
|
||||
"""
|
||||
return self.image_processor.calc_num_image_tokens_from_image_size(width, height)
|
||||
|
||||
|
||||
@property
|
||||
def special_image_token_id(self):
|
||||
return self.tokenizer.convert_tokens_to_ids(self.special_image_token)
|
||||
|
||||
def get_special_image_token_id(self):
|
||||
return self.tokenizer.convert_tokens_to_ids(self.special_image_token)
|
||||
|
||||
def _convert_images_texts_to_inputs(self, images, texts, padding=False, truncation=None, max_length=None, return_tensors=None):
|
||||
|
||||
if not len(images):
|
||||
model_inputs = self.tokenizer(texts, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length)
|
||||
return BatchFeature(data={**model_inputs})
|
||||
|
||||
pattern = r"<\|image_\d+\|>"
|
||||
prompt_chunks = [self.tokenizer(chunk).input_ids for chunk in re.split(pattern, texts)]
|
||||
|
||||
if 'num_img_tokens' in images:
|
||||
num_img_tokens = images['num_img_tokens']
|
||||
else:
|
||||
assert 'num_crops' in images, 'num_crops must be provided in images if num_img_tokens is not provided'
|
||||
num_crops = images['num_crops']
|
||||
num_img_tokens = [_num_crops * self.num_img_tokens for _num_crops in num_crops]
|
||||
|
||||
images, image_sizes = images['pixel_values'], images['image_sizes']
|
||||
|
||||
# image_tags needs to start from 1 to n
|
||||
image_tags = re.findall(pattern, texts)
|
||||
# image_ids = [int(s.split("|")[1].split("_")[-1]) * -1 for s in image_tags]
|
||||
# image_ids_pad = [[iid]*num_img_tokens[i] for i, iid in enumerate(image_ids)]
|
||||
image_ids = [int(s.split("|")[1].split("_")[-1]) for s in image_tags]
|
||||
unique_image_ids = sorted(list(set(image_ids)))
|
||||
# image_ids must start from 1, and must be continuous int, e.g. [1, 2, 3], cannot be [1, 4, 5]
|
||||
# check the condition
|
||||
assert unique_image_ids == list(range(1, len(unique_image_ids)+1)), f"image_ids must start from 1, and must be continuous int, e.g. [1, 2, 3], cannot be {unique_image_ids}"
|
||||
# total images must be the same as the number of image tags
|
||||
assert len(unique_image_ids) == len(images), f"total images must be the same as the number of image tags, got {len(unique_image_ids)} image tags and {len(images)} images"
|
||||
|
||||
image_ids_pad = [[-iid]*num_img_tokens[iid-1] for iid in image_ids]
|
||||
|
||||
def insert_separator(X, sep_list):
|
||||
if len(X) > len(sep_list):
|
||||
sep_list.append([])
|
||||
return [ele for sublist in zip(X, sep_list) for ele in sublist]
|
||||
input_ids = []
|
||||
offset = 0
|
||||
for x in insert_separator(prompt_chunks, image_ids_pad):
|
||||
input_ids.extend(x[offset:])
|
||||
|
||||
input_ids = torch.tensor(input_ids, dtype=torch.long).unsqueeze(0)
|
||||
attention_mask = (input_ids > -1000000).to(torch.long)
|
||||
|
||||
return BatchFeature(data={"input_ids": input_ids,
|
||||
"attention_mask": attention_mask,
|
||||
"pixel_values": images,
|
||||
"image_sizes": image_sizes})
|
||||
|
||||
|
||||
# Copied from transformers.models.clip.processing_clip.CLIPProcessor.batch_decode with CLIP->Llama
|
||||
def batch_decode(self, *args, **kwargs):
|
||||
"""
|
||||
This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
|
||||
refer to the docstring of this method for more information.
|
||||
"""
|
||||
return self.tokenizer.batch_decode(*args, **kwargs)
|
||||
|
||||
# Copied from transformers.models.clip.processing_clip.CLIPProcessor.decode with CLIP->Llama
|
||||
def decode(self, *args, **kwargs):
|
||||
"""
|
||||
This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
|
||||
the docstring of this method for more information.
|
||||
"""
|
||||
return self.tokenizer.decode(*args, **kwargs)
|
||||
|
||||
@property
|
||||
# Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names
|
||||
def model_input_names(self):
|
||||
tokenizer_input_names = self.tokenizer.model_input_names
|
||||
image_processor_input_names = self.image_processor.model_input_names
|
||||
return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))
|
||||
6
processor_config.json
Normal file
6
processor_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"auto_map": {
|
||||
"AutoProcessor": "processing_phi3_v.Phi3VProcessor"
|
||||
},
|
||||
"processor_class": "Phi3VProcessor"
|
||||
}
|
||||
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 sha256:770f1942a3cacbdabd63cfdb573be46c510527c751cb9ecf5a691fab7ac30a34
|
||||
size 4944243099
|
||||
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:c990a2ac0f24e220aa4c75fc8a2a672eb24d050f61c08e58c17c07445d039b74
|
||||
size 3349229092
|
||||
600
pytorch_model.bin.index.json
Normal file
600
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,600 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8293242880
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.18.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.19.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.19.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.20.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.20.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.21.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.21.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.norm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.vision_embed_tokens.glb_GN": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_processor.vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_projection.0.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_projection.0.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_projection.2.bias": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.img_projection.2.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.sub_GN": "pytorch_model-00001-of-00002.bin",
|
||||
"model.vision_embed_tokens.wte.weight": "pytorch_model-00001-of-00002.bin"
|
||||
}
|
||||
}
|
||||
36
special_tokens_map.json
Normal file
36
special_tokens_map.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|system|>",
|
||||
"<|end|>",
|
||||
"<|user|>",
|
||||
"<|end|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93796
tokenizer.json
Normal file
93796
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
412
tokenizer_config.json
Normal file
412
tokenizer_config.json
Normal file
@@ -0,0 +1,412 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32002": {
|
||||
"content": "<|placeholder1|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32003": {
|
||||
"content": "<|placeholder2|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32004": {
|
||||
"content": "<|placeholder3|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32005": {
|
||||
"content": "<|placeholder4|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32006": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32007": {
|
||||
"content": "<|end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32008": {
|
||||
"content": "<|placeholder5|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32009": {
|
||||
"content": "<|placeholder6|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32010": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32011": {
|
||||
"content": "<|placeholder7|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32012": {
|
||||
"content": "<|placeholder8|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32013": {
|
||||
"content": "<|placeholder9|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32014": {
|
||||
"content": "<|placeholder10|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32015": {
|
||||
"content": "<|placeholder11|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32016": {
|
||||
"content": "<|placeholder12|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32017": {
|
||||
"content": "<|placeholder13|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32018": {
|
||||
"content": "<|placeholder14|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32019": {
|
||||
"content": "<|placeholder15|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32020": {
|
||||
"content": "<|placeholder16|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32021": {
|
||||
"content": "<|placeholder17|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32022": {
|
||||
"content": "<|placeholder18|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32023": {
|
||||
"content": "<|placeholder19|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32024": {
|
||||
"content": "<|placeholder20|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32025": {
|
||||
"content": "<|placeholder21|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32026": {
|
||||
"content": "<|placeholder22|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32027": {
|
||||
"content": "<|placeholder23|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32028": {
|
||||
"content": "<|placeholder24|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32029": {
|
||||
"content": "<|placeholder25|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32030": {
|
||||
"content": "<|placeholder26|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32031": {
|
||||
"content": "<|placeholder27|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32032": {
|
||||
"content": "<|placeholder28|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32033": {
|
||||
"content": "<|placeholder29|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32034": {
|
||||
"content": "<|placeholder30|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32035": {
|
||||
"content": "<|placeholder31|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32036": {
|
||||
"content": "<|placeholder32|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32037": {
|
||||
"content": "<|placeholder33|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32038": {
|
||||
"content": "<|placeholder34|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32039": {
|
||||
"content": "<|placeholder35|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32040": {
|
||||
"content": "<|placeholder36|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32041": {
|
||||
"content": "<|placeholder37|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32042": {
|
||||
"content": "<|placeholder38|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32043": {
|
||||
"content": "<|placeholder39|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32044": {
|
||||
"content": "<|image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|system|>",
|
||||
"<|end|>",
|
||||
"<|user|>",
|
||||
"<|end|>"
|
||||
],
|
||||
"auto_map": {
|
||||
"AutoProcessor": "processing_phi3_v.Phi3VProcessor"
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"legacy": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"processor_class": "Phi3VProcessor",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user