first commit
This commit is contained in:
xxl
parent
c416ab7a24
commit
3183f447e1
145
README.md
145
README.md
|
|
@ -1,3 +1,144 @@
|
|||
# gme-Qwen2-VL-7B-Instruct
|
||||
---
|
||||
frameworks:
|
||||
- Pytorch
|
||||
license: Apache License 2.0
|
||||
tasks:
|
||||
- multi-modal-embedding
|
||||
|
||||
gme-Qwen2-VL-7B-Instruct
|
||||
#model-type:
|
||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||||
#- gpt
|
||||
|
||||
#domain:
|
||||
##如 nlp、cv、audio、multi-modal
|
||||
#- nlp
|
||||
|
||||
#language:
|
||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||||
#- cn
|
||||
|
||||
#metrics:
|
||||
##如 CIDEr、Blue、ROUGE 等
|
||||
#- CIDEr
|
||||
|
||||
#tags:
|
||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||||
#- pretrained
|
||||
|
||||
#tools:
|
||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||||
#- vllm
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen2-VL-7B-Instruct
|
||||
metrics:
|
||||
- accuracy
|
||||
---
|
||||
|
||||
## GME-Qwen2-VL-7B
|
||||
|
||||
`GME-Qwen2VL` 系列统一的**多模态Embedding模型**基于[Qwen2-VL](https://modelscope.cn/models/Qwen/Qwen2-VL-7B-Instruct) 多模态大型语言模型 (MLLMs)训练。`GME` 模型支持三种类型的输入：**文本**、**图像**和**图像-文本对**，所有这些输入类型都可以生成通用的向量表示，并具有优秀的检索性能。
|
||||
|
||||
**GME模型主要特点**:
|
||||
|
||||
- **统一的多模态表示**：GME 模型可以处理单一模态和组合模态的输入，生成统一的向量表示。这使得各种检索场景（Any2Any 搜索）成为可能，支持如文本检索、从文本检索图像以及图像之间的检索等任务。
|
||||
- **高性能**：在我们的通用多模态检索基准 (**UMRB**) 中达到了最先进 (SOTA) 的结果，并在多语言文本评估基准 (**MTEB**) 中表现优异。
|
||||
- **动态图像分辨率**：受益于 `Qwen2-VL`的特性，GME模型支持动态分辨率的图像输入。
|
||||
- **强大的视觉检索性能**：得益于Qwen2-VL模型系列和训练数据，我们的模型在视觉文档检索任务(例如表格PDF检索)中表现优异。这一能力对于复杂的文档理解场景尤为重要，例如专注于学术论文的多模态检索增强生成 (RAG) 应用。
|
||||
|
||||
**Paper**: [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](http://arxiv.org/abs/2412.16855)
|
||||
|
||||
## Model List
|
||||
| Models | Model Size | Max Seq. Length | Dimension | MTEB-en| MTEB-zh | UMRB |
|
||||
|:-----: | :-----: |:-----: |:-----: |:-----: | :-----: | :-----: |
|
||||
|[`gme-Qwen2-VL-2B`](https://modelscope.cn/models/iic/gme-Qwen2-VL-2B-Instruct) | 2.21B | 32768 | 1536 | 65.27 | 68.41 | 64.45 |
|
||||
|[`gme-Qwen2-VL-7B`](https://modelscope.cn/models/iic/gme-Qwen2-VL-7B-Instruct) | 8.29B | 32768 | 3584 | 67.48 | 71.36 | 67.44 |
|
||||
|
||||
## Usage
|
||||
**Use with custom code**
|
||||
|
||||
```python
|
||||
# You can find the script gme_inference.py in https://modelscope.cn/models/iic/gme-Qwen2-VL-7B-Instruct/file/view/master?fileName=gme_inference.py
|
||||
from gme_inference import GmeQwen2VL
|
||||
|
||||
texts = [
|
||||
"What kind of car is this?",
|
||||
"The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023."
|
||||
]
|
||||
images = [
|
||||
'https://mitalinlp.oss-cn-hangzhou.aliyuncs.com/test/Tesla_Cybertruck_damaged_window.jpg',
|
||||
'https://mitalinlp.oss-cn-hangzhou.aliyuncs.com/test/2024_Tesla_Cybertruck_Foundation_Series%2C_front_left_(Greenwich).jpg',
|
||||
]
|
||||
|
||||
gme = GmeQwen2VL("gme-Qwen2-VL-7B-Instruct")
|
||||
|
||||
# Single-modal embedding
|
||||
e_text = gme.get_text_embeddings(texts=texts)
|
||||
e_image = gme.get_image_embeddings(images=images)
|
||||
print((e_text * e_image).sum(-1))
|
||||
## tensor([0.2281, 0.6001], dtype=torch.float16)
|
||||
|
||||
# How to set embedding instruction
|
||||
e_query = gme.get_text_embeddings(texts=texts, instruction='Find an image that matches the given text.')
|
||||
# If is_query=False, we always use the default instruction.
|
||||
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
|
||||
print((e_query * e_corpus).sum(-1))
|
||||
## tensor([0.2433, 0.7051], dtype=torch.float16)
|
||||
|
||||
# Fused-modal embedding
|
||||
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
|
||||
print((e_fused[0] * e_fused[1]).sum())
|
||||
## tensor(0.6108, dtype=torch.float16)
|
||||
|
||||
```
|
||||
|
||||
## UMRB评测
|
||||
|
||||
|
||||
| | | Single-modal | | Cross-modal | | | Fused-modal | | | | Avg. |
|
||||
|--------------------|------|:------------:|:---------:|:-----------:|:-----------:|:---------:|:-----------:|:----------:|:----------:|:-----------:|:----------:|
|
||||
| | | T→T (16) | I→I (1) | T→I (4) | T→VD (10) | I→T (4) | T→IT (2) | IT→T (5) | IT→I (2) | IT→IT (3) | (47) |
|
||||
| VISTA | 0.2B | 55.15 | **31.98** | 32.88 | 10.12 | 31.23 | 45.81 | 53.32 | 8.97 | 26.26 | 37.32 |
|
||||
| CLIP-SF | 0.4B | 39.75 | 31.42 | 59.05 | 24.09 | 62.95 | 66.41 | 53.32 | 34.9 | 55.65 | 43.66 |
|
||||
| One-Peace | 4B | 43.54 | 31.27 | 61.38 | 42.9 | 65.59 | 42.72 | 28.29 | 6.73 | 23.41 | 42.01 |
|
||||
| DSE | 4.2B | 48.94 | 27.92 | 40.75 | 78.21 | 52.54 | 49.62 | 35.44 | 8.36 | 40.18 | 50.04 |
|
||||
| E5-V | 8.4B | 52.41 | 27.36 | 46.56 | 41.22 | 47.95 | 54.13 | 32.9 | 23.17 | 7.23 | 42.52 |
|
||||
| **[GME-Qwen2-VL-2B](https://modelscope.cn/models/iic/gme-Qwen2-VL-2B-Instruct)** | 2.2B | 55.93 | 29.86 | 57.36 | 87.84 | 61.93 | 76.47 | 64.58 | 37.02 | 66.47 | 64.45 |
|
||||
| **[GME-Qwen2-VL-7B](https://modelscope.cn/models/iic/gme-Qwen2-VL-7B-Instruct)** | 8.3B | **58.19** | 31.89 | **61.35** | **89.92** | **65.83** | **80.94** | **66.18** | **42.56** | **73.62** | **67.44** |
|
||||
|
||||
The [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) English tab shows the text embeddings performence of our model.
|
||||
|
||||
**更详细的实验结果可以在[论文](http://arxiv.org/abs/2412.16855)中找到**。
|
||||
|
||||
|
||||
## 限制
|
||||
|
||||
- **单图像输入**：为了获得较好的训练效率，我们将视觉标记的数量限制为1024。由于相关数据的缺乏，我们的模型和评估仅保留单一图像。
|
||||
- **单语训练**：我们的模型仅在英语数据上进行训练。尽管`Qwen2-VL`模型是多语言的，但多语言多模态Embedding嵌入的性能不能完全保证
|
||||
|
||||
我们将在未来的版本中扩展到多图像输入、图文交错的数据以及多语言数据。
|
||||
|
||||
## 阿里云API服务
|
||||
|
||||
除了开源的[GME](https://modelscope.cn/models/iic/gme-Qwen2-VL-2B-Instruct/file/edit/master?fileName=README.md)系列模型，GME模型也可以作为商业API服务在阿里云上使用。
|
||||
|
||||
- [多模态向量模型](https://help.aliyun.com/zh/model-studio/developer-reference/multimodal-embedding-api-reference?spm=a2c4g.11186623.0.0.321c1d1cqmoJ5C)：提供 `multimodal-embedding-v1` 模型服务。
|
||||
|
||||
请注意，商业API背后的模型与开源模型并不完全相同。
|
||||
|
||||
## 引用
|
||||
如果您发现我们的论文或模型对您有帮助，请考虑引用：
|
||||
|
||||
```
|
||||
@misc{zhang2024gme,
|
||||
title={GME: Improving Universal Multimodal Retrieval by Multimodal LLMs},
|
||||
author={Zhang, Xin and Zhang, Yanzhao and Xie, Wen and Li, Mingxin and Dai, Ziqi and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Li, Wenjie and Zhang, Min},
|
||||
year={2024},
|
||||
eprint={2412.16855},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={http://arxiv.org/abs/2412.16855},
|
||||
}
|
||||
```
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
{
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
{
|
||||
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
{
|
||||
"_name_or_path": "gme-Qwen2-VL-7B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"type": "mrope"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.45.0.dev0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"in_chans": 3,
|
||||
"model_type": "qwen2_vl",
|
||||
"spatial_patch_size": 14
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
|
|
@ -0,0 +1 @@
|
|||
{"framework":"Pytorch","task":"multi-modal-embedding"}
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.01,
|
||||
"top_k": 1,
|
||||
"top_p": 0.001,
|
||||
"transformers_version": "4.45.0.dev0"
|
||||
}
|
||||
|
|
@ -0,0 +1,299 @@
|
|||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
from functools import partial
|
||||
from typing import Dict, List, Literal, Optional
|
||||
|
||||
import torch
|
||||
from PIL import Image
|
||||
from torch.utils.data import DataLoader
|
||||
from tqdm.autonotebook import tqdm
|
||||
from transformers import AutoModelForVision2Seq, AutoProcessor
|
||||
|
||||
|
||||
class GmeQwen2VL:
|
||||
def __init__(
|
||||
self,
|
||||
model_name: str = "gme-Qwen2-VL-7B-Instruct",
|
||||
model_path: Optional[str] = None,
|
||||
device: str = "cuda" if torch.cuda.is_available() else "cpu",
|
||||
min_image_tokens=256,
|
||||
max_image_tokens=1280,
|
||||
max_length=1800,
|
||||
**kwargs,
|
||||
) -> None:
|
||||
model_name = model_path or model_name
|
||||
self.base = AutoModelForVision2Seq.from_pretrained(
|
||||
model_name, torch_dtype=torch.float16, **kwargs
|
||||
)
|
||||
self.base.eval()
|
||||
self.normalize = True
|
||||
self.device = device
|
||||
min_pixels = min_image_tokens * 28 * 28
|
||||
max_pixels = max_image_tokens * 28 * 28
|
||||
self.max_length = max_length
|
||||
self.processor = AutoProcessor.from_pretrained(
|
||||
model_name, min_pixels=min_pixels, max_pixels=max_pixels, **kwargs
|
||||
)
|
||||
self.processor.tokenizer.padding_side = 'right'
|
||||
self.defualt_instruction = 'You are a helpful assistant.'
|
||||
self.sep = ' '
|
||||
|
||||
def forward(
|
||||
self,
|
||||
input_ids: Optional[torch.LongTensor] = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.LongTensor] = None,
|
||||
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
||||
inputs_embeds: Optional[torch.FloatTensor] = None,
|
||||
pixel_values: Optional[torch.Tensor] = None,
|
||||
# pixel_values_videos: Optional[torch.FloatTensor] = None,
|
||||
image_grid_thw: Optional[torch.LongTensor] = None,
|
||||
# video_grid_thw: Optional[torch.LongTensor] = None,
|
||||
pooling_mask: Optional[torch.LongTensor] = None,
|
||||
**kwargs
|
||||
) -> torch.Tensor:
|
||||
if inputs_embeds is None:
|
||||
inputs_embeds = self.base.model.embed_tokens(input_ids)
|
||||
if pixel_values is not None:
|
||||
pixel_values = pixel_values.type(self.base.visual.get_dtype())
|
||||
image_embeds = self.base.visual(pixel_values, grid_thw=image_grid_thw).to(inputs_embeds.device)
|
||||
image_mask = input_ids == self.base.config.image_token_id
|
||||
inputs_embeds[image_mask] = image_embeds
|
||||
# if pixel_values_videos is not None:
|
||||
# pixel_values_videos = pixel_values_videos.type(self.base.visual.get_dtype())
|
||||
# video_embeds = self.base.visual(pixel_values_videos, grid_thw=video_grid_thw).to(inputs_embeds.device)
|
||||
# video_mask = input_ids == self.base.config.video_token_id
|
||||
# inputs_embeds[video_mask] = video_embeds
|
||||
if attention_mask is not None:
|
||||
attention_mask = attention_mask.to(inputs_embeds.device)
|
||||
|
||||
outputs = self.base.model(
|
||||
input_ids=None,
|
||||
position_ids=position_ids,
|
||||
attention_mask=attention_mask,
|
||||
past_key_values=past_key_values,
|
||||
inputs_embeds=inputs_embeds,
|
||||
)
|
||||
|
||||
pooling_mask = attention_mask if pooling_mask is None else pooling_mask
|
||||
left_padding = (pooling_mask[:, -1].sum() == pooling_mask.shape[0]) # TODO
|
||||
if left_padding:
|
||||
embeddings = outputs.last_hidden_state[:, -1]
|
||||
else:
|
||||
sequence_lengths = pooling_mask.sum(dim=1) - 1
|
||||
batch_size = outputs.last_hidden_state.shape[0]
|
||||
embeddings = outputs.last_hidden_state[torch.arange(
|
||||
batch_size, device=outputs.last_hidden_state.device
|
||||
), sequence_lengths]
|
||||
if self.normalize:
|
||||
embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1)
|
||||
return embeddings.contiguous()
|
||||
|
||||
def embed(self, texts: list[str], images: list[Image.Image], is_query=True, instruction=None, **kwargs):
|
||||
self.base.to(self.device)
|
||||
# Inputs must be batched
|
||||
input_texts, input_images = list(), list()
|
||||
for t, i in zip(texts, images):
|
||||
if not is_query or instruction is None:
|
||||
instruction = self.defualt_instruction
|
||||
input_str = ''
|
||||
if i is None:
|
||||
input_images = None # All examples in the same batch are consistent
|
||||
else:
|
||||
input_str += '<|vision_start|><|image_pad|><|vision_end|>'
|
||||
i = fetch_image(i)
|
||||
input_images.append(i)
|
||||
if t is not None:
|
||||
input_str += t
|
||||
msg = f'<|im_start|>system\n{instruction}<|im_end|>\n<|im_start|>user\n{input_str}<|im_end|>\n<|im_start|>assistant\n<|endoftext|>'
|
||||
input_texts.append(msg)
|
||||
|
||||
inputs = self.processor(
|
||||
text=input_texts,
|
||||
images=input_images,
|
||||
padding=True,
|
||||
truncation=True,
|
||||
max_length=self.max_length,
|
||||
return_tensors='pt'
|
||||
)
|
||||
inputs = {k: v.to(self.device) for k, v in inputs.items()} # TODO
|
||||
with torch.no_grad():
|
||||
embeddings = self.forward(**inputs)
|
||||
return embeddings
|
||||
|
||||
def encode(self, sentences: list[str], *, prompt_name=None, **kwargs):
|
||||
return self.get_fused_embeddings(texts=sentences, prompt_name=prompt_name, **kwargs)
|
||||
|
||||
def encode_queries(self, queries: List[str], **kwargs):
|
||||
embeddings = self.encode(queries, **kwargs)
|
||||
return embeddings
|
||||
|
||||
def encode_corpus(self, corpus: List[Dict[str, str]], **kwargs):
|
||||
if type(corpus) is dict:
|
||||
sentences = [
|
||||
(corpus["title"][i] + self.sep + corpus["text"][i]).strip()
|
||||
if "title" in corpus
|
||||
else corpus["text"][i].strip()
|
||||
for i in range(len(corpus["text"]))
|
||||
]
|
||||
else:
|
||||
sentences = [
|
||||
(doc["title"] + self.sep + doc["text"]).strip() if "title" in doc else doc["text"].strip()
|
||||
for doc in corpus
|
||||
]
|
||||
embeddings = self.encode(sentences, is_query=False, **kwargs)
|
||||
return embeddings
|
||||
|
||||
def get_image_embeddings(self, images: list[Image.Image] | DataLoader, **kwargs):
|
||||
return self.get_fused_embeddings(images=images, **kwargs)
|
||||
|
||||
def get_text_embeddings(self, texts: list[str], **kwargs):
|
||||
return self.get_fused_embeddings(texts=texts, **kwargs)
|
||||
|
||||
def get_fused_embeddings(self, texts: list[str] = None, images: list[Image.Image] | DataLoader = None, **kwargs):
|
||||
if isinstance(images, DataLoader):
|
||||
image_loader = images
|
||||
batch_size = image_loader.batch_size
|
||||
image_loader.dataset.transform = None
|
||||
else:
|
||||
batch_size = kwargs.pop('batch_size', 32)
|
||||
if images is None:
|
||||
image_loader = None
|
||||
else:
|
||||
image_loader = DataLoader(
|
||||
images,
|
||||
batch_size=batch_size,
|
||||
shuffle=False,
|
||||
collate_fn=custom_collate_fn,
|
||||
num_workers=min(math.floor(os.cpu_count() / 2), 8),
|
||||
)
|
||||
|
||||
if texts is None:
|
||||
assert image_loader is not None
|
||||
n_batch = len(image_loader)
|
||||
else:
|
||||
n_batch = len(texts) // batch_size + int(len(texts) % batch_size > 0)
|
||||
image_loader = image_loader or [None] * n_batch
|
||||
|
||||
all_embeddings = list()
|
||||
none_batch = [None] * batch_size
|
||||
show_progress_bar = kwargs.pop('show_progress_bar', True)
|
||||
pbar = tqdm(total=n_batch, disable=not show_progress_bar, mininterval=1, miniters=10, desc='encode')
|
||||
for n, img_batch in zip(range(0, n_batch * batch_size, batch_size), image_loader):
|
||||
text_batch = none_batch if texts is None else texts[n: n+batch_size]
|
||||
img_batch = none_batch if img_batch is None else img_batch
|
||||
embeddings = self.embed(texts=text_batch, images=img_batch, **kwargs)
|
||||
pbar.update(1)
|
||||
all_embeddings.append(embeddings.cpu())
|
||||
pbar.close()
|
||||
all_embeddings = torch.cat(all_embeddings, dim=0)
|
||||
return all_embeddings
|
||||
|
||||
|
||||
def custom_collate_fn(batch):
|
||||
return batch
|
||||
|
||||
|
||||
### Copied from qwen_vl_utils.vision_process.py
|
||||
import base64
|
||||
from io import BytesIO
|
||||
import requests
|
||||
|
||||
IMAGE_FACTOR = 28
|
||||
MIN_PIXELS = 4 * 28 * 28
|
||||
MAX_PIXELS = 16384 * 28 * 28
|
||||
MAX_RATIO = 200
|
||||
|
||||
|
||||
def round_by_factor(number: int, factor: int) -> int:
|
||||
"""Returns the closest integer to 'number' that is divisible by 'factor'."""
|
||||
return round(number / factor) * factor
|
||||
|
||||
|
||||
def ceil_by_factor(number: int, factor: int) -> int:
|
||||
"""Returns the smallest integer greater than or equal to 'number' that is divisible by 'factor'."""
|
||||
return math.ceil(number / factor) * factor
|
||||
|
||||
|
||||
def floor_by_factor(number: int, factor: int) -> int:
|
||||
"""Returns the largest integer less than or equal to 'number' that is divisible by 'factor'."""
|
||||
return math.floor(number / factor) * factor
|
||||
|
||||
|
||||
def smart_resize(
|
||||
height: int, width: int, factor: int = IMAGE_FACTOR, min_pixels: int = MIN_PIXELS, max_pixels: int = MAX_PIXELS
|
||||
) -> tuple[int, int]:
|
||||
"""
|
||||
Rescales the image so that the following conditions are met:
|
||||
|
||||
1. Both dimensions (height and width) are divisible by 'factor'.
|
||||
|
||||
2. The total number of pixels is within the range ['min_pixels', 'max_pixels'].
|
||||
|
||||
3. The aspect ratio of the image is maintained as closely as possible.
|
||||
"""
|
||||
h_bar = max(factor, round_by_factor(height, factor))
|
||||
w_bar = max(factor, round_by_factor(width, factor))
|
||||
if h_bar * w_bar > max_pixels:
|
||||
beta = math.sqrt((height * width) / max_pixels)
|
||||
h_bar = floor_by_factor(height / beta, factor)
|
||||
w_bar = floor_by_factor(width / beta, factor)
|
||||
elif h_bar * w_bar < min_pixels:
|
||||
beta = math.sqrt(min_pixels / (height * width))
|
||||
h_bar = ceil_by_factor(height * beta, factor)
|
||||
w_bar = ceil_by_factor(width * beta, factor)
|
||||
|
||||
if max(h_bar, w_bar) / min(h_bar, w_bar) > MAX_RATIO:
|
||||
logging.warning(
|
||||
f"Absolute aspect ratio must be smaller than {MAX_RATIO}, got {max(h_bar, w_bar) / min(h_bar, w_bar)}"
|
||||
)
|
||||
if h_bar > w_bar:
|
||||
h_bar = w_bar * MAX_RATIO
|
||||
else:
|
||||
w_bar = h_bar * MAX_RATIO
|
||||
return h_bar, w_bar
|
||||
|
||||
|
||||
def fetch_image(image: str | Image.Image, size_factor: int = IMAGE_FACTOR) -> Image.Image:
|
||||
image_obj = None
|
||||
if isinstance(image, Image.Image):
|
||||
image_obj = image
|
||||
elif image.startswith("http://") or image.startswith("https://"):
|
||||
image_obj = Image.open(requests.get(image, stream=True).raw)
|
||||
elif image.startswith("file://"):
|
||||
image_obj = Image.open(image[7:])
|
||||
elif image.startswith("data:image"):
|
||||
if "base64," in image:
|
||||
_, base64_data = image.split("base64,", 1)
|
||||
data = base64.b64decode(base64_data)
|
||||
image_obj = Image.open(BytesIO(data))
|
||||
else:
|
||||
image_obj = Image.open(image)
|
||||
if image_obj is None:
|
||||
raise ValueError(f"Unrecognized image input, support local path, http url, base64 and PIL.Image, got {image}")
|
||||
image = image_obj.convert("RGB")
|
||||
## resize
|
||||
# if "resized_height" in ele and "resized_width" in ele:
|
||||
# resized_height, resized_width = smart_resize(
|
||||
# ele["resized_height"],
|
||||
# ele["resized_width"],
|
||||
# factor=size_factor,
|
||||
# )
|
||||
# else:
|
||||
width, height = image.size
|
||||
# min_pixels = ele.get("min_pixels", MIN_PIXELS)
|
||||
# max_pixels = ele.get("max_pixels", MAX_PIXELS)
|
||||
resized_height, resized_width = smart_resize(
|
||||
height,
|
||||
width,
|
||||
factor=size_factor,
|
||||
min_pixels=MIN_PIXELS,
|
||||
max_pixels=MAX_PIXELS,
|
||||
)
|
||||
image = image.resize((resized_width, resized_height))
|
||||
|
||||
return image
|
||||
###
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 513 KiB |
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1,737 @@
|
|||
{
|
||||
"metadata": {
|
||||
"total_size": 33165502464
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00009-of-00009.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00009.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.mlp.fc1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.mlp.fc1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.mlp.fc2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.mlp.fc2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.norm1.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.norm2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.merger.ln_q.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00001-of-00009.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00009.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
{
|
||||
"min_pixels": 3136,
|
||||
"max_pixels": 12845056,
|
||||
"patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"merge_size": 2,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessor",
|
||||
"processor_class": "Qwen2VLProcessor"
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1,31 @@
|
|||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,143 @@
|
|||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue