初始化项目，由ModelHub XC社区提供模型
Model: OS-Copilot/OS-Atlas-Base-4B Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
155
README.md
Normal file
155
README.md
Normal file
@@ -0,0 +1,155 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
base_model: OpenGVLab/InternVL2-4B
|
||||
pipeline_tag: image-text-to-text
|
||||
---
|
||||
|
||||
# OS-Atlas: A Foundation Action Model For Generalist GUI Agents
|
||||
|
||||
<div align="center">
|
||||
|
||||
[\[🏠Homepage\]](https://osatlas.github.io) [\[💻Code\]](https://github.com/OS-Copilot/OS-Atlas) [\[🚀Quick Start\]](#quick-start) [\[📝Paper\]](https://arxiv.org/abs/2410.23218) [\[🤗Models\]](https://huggingface.co/collections/OS-Copilot/os-atlas-67246e44003a1dfcc5d0d045)[\[🤗Data\]](https://huggingface.co/datasets/OS-Copilot/OS-Atlas-data) [\[🤗ScreenSpot-v2\]](https://huggingface.co/datasets/OS-Copilot/ScreenSpot-v2)
|
||||
|
||||
</div>
|
||||
|
||||
## Overview
|
||||
|
||||
|
||||
OS-Atlas provides a series of models specifically designed for GUI agents.
|
||||
|
||||
For GUI grounding tasks, you can use:
|
||||
- [OS-Atlas-Base-7B](https://huggingface.co/OS-Copilot/OS-Atlas-Base-7B)
|
||||
- [OS-Atlas-Base-4B](https://huggingface.co/OS-Copilot/OS-Atlas-Base-4B)
|
||||
|
||||
For generating single-step actions in GUI agent tasks, you can use:
|
||||
- [OS-Atlas-Pro-7B](https://huggingface.co/OS-Copilot/OS-Atlas-Pro-7B)
|
||||
- [OS-Atlas-Pro-4B](https://huggingface.co/OS-Copilot/OS-Atlas-Pro-4B)
|
||||
|
||||
## Quick Start
|
||||
OS-Atlas-Base-4B is a GUI grounding model finetuned from [InternVL2-4B](https://huggingface.co/OpenGVLab/InternVL2-4B).
|
||||
|
||||
**Notes:** Our models accept images of any size as input. The model outputs are normalized to relative coordinates within a 0-1000 range (either a center point or a bounding box defined by top-left and bottom-right coordinates). For visualization, please remember to convert these relative coordinates back to the original image dimensions.
|
||||
|
||||
### Inference Example
|
||||
First, install the `transformers` library:
|
||||
```
|
||||
pip install transformers
|
||||
```
|
||||
For additional dependencies, please refer to the [InternVL2 documentation](https://internvl.readthedocs.io/en/latest/get_started/installation.html)
|
||||
|
||||
Then download the [example image](https://github.com/OS-Copilot/OS-Atlas/blob/main/examples/images/web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png) and save it to the current directory.
|
||||
|
||||
Inference code example:
|
||||
```python
|
||||
import numpy as np
|
||||
import torch
|
||||
import torchvision.transforms as T
|
||||
from PIL import Image
|
||||
from torchvision.transforms.functional import InterpolationMode
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
IMAGENET_MEAN = (0.485, 0.456, 0.406)
|
||||
IMAGENET_STD = (0.229, 0.224, 0.225)
|
||||
|
||||
def build_transform(input_size):
|
||||
MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
|
||||
transform = T.Compose([
|
||||
T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
|
||||
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
|
||||
T.ToTensor(),
|
||||
T.Normalize(mean=MEAN, std=STD)
|
||||
])
|
||||
return transform
|
||||
|
||||
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
|
||||
best_ratio_diff = float('inf')
|
||||
best_ratio = (1, 1)
|
||||
area = width * height
|
||||
for ratio in target_ratios:
|
||||
target_aspect_ratio = ratio[0] / ratio[1]
|
||||
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
|
||||
if ratio_diff < best_ratio_diff:
|
||||
best_ratio_diff = ratio_diff
|
||||
best_ratio = ratio
|
||||
elif ratio_diff == best_ratio_diff:
|
||||
if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
|
||||
best_ratio = ratio
|
||||
return best_ratio
|
||||
|
||||
def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
|
||||
orig_width, orig_height = image.size
|
||||
aspect_ratio = orig_width / orig_height
|
||||
|
||||
# calculate the existing image aspect ratio
|
||||
target_ratios = set(
|
||||
(i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
|
||||
i * j <= max_num and i * j >= min_num)
|
||||
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
|
||||
|
||||
# find the closest aspect ratio to the target
|
||||
target_aspect_ratio = find_closest_aspect_ratio(
|
||||
aspect_ratio, target_ratios, orig_width, orig_height, image_size)
|
||||
|
||||
# calculate the target width and height
|
||||
target_width = image_size * target_aspect_ratio[0]
|
||||
target_height = image_size * target_aspect_ratio[1]
|
||||
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
|
||||
|
||||
# resize the image
|
||||
resized_img = image.resize((target_width, target_height))
|
||||
processed_images = []
|
||||
for i in range(blocks):
|
||||
box = (
|
||||
(i % (target_width // image_size)) * image_size,
|
||||
(i // (target_width // image_size)) * image_size,
|
||||
((i % (target_width // image_size)) + 1) * image_size,
|
||||
((i // (target_width // image_size)) + 1) * image_size
|
||||
)
|
||||
# split the image
|
||||
split_img = resized_img.crop(box)
|
||||
processed_images.append(split_img)
|
||||
assert len(processed_images) == blocks
|
||||
if use_thumbnail and len(processed_images) != 1:
|
||||
thumbnail_img = image.resize((image_size, image_size))
|
||||
processed_images.append(thumbnail_img)
|
||||
return processed_images
|
||||
|
||||
def load_image(image_file, input_size=448, max_num=12):
|
||||
image = Image.open(image_file).convert('RGB')
|
||||
transform = build_transform(input_size=input_size)
|
||||
images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
|
||||
pixel_values = [transform(image) for image in images]
|
||||
pixel_values = torch.stack(pixel_values)
|
||||
return pixel_values
|
||||
|
||||
# If you want to load a model using multiple GPUs, please refer to the `Multiple GPUs` section.
|
||||
path = 'OS-Copilot/OS-Atlas-Base-4B'
|
||||
model = AutoModel.from_pretrained(
|
||||
path,
|
||||
torch_dtype=torch.bfloat16,
|
||||
low_cpu_mem_usage=True,
|
||||
trust_remote_code=True).eval().cuda()
|
||||
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
|
||||
|
||||
# set the max number of tiles in `max_num`
|
||||
pixel_values = load_image('./web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png', max_num=6).to(torch.bfloat16).cuda()
|
||||
generation_config = dict(max_new_tokens=1024, do_sample=True)
|
||||
|
||||
question = "In the screenshot of this web page, please give me the coordinates of the element I want to click on according to my instructions(with point).\n\"'Champions League' link\""
|
||||
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
|
||||
print(f'User: {question}\nAssistant: {response}')
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
## Citation
|
||||
If you find this repository helpful, feel free to cite our paper:
|
||||
```bibtex
|
||||
@article{wu2024atlas,
|
||||
title={OS-ATLAS: A Foundation Action Model for Generalist GUI Agents},
|
||||
author={Wu, Zhiyong and Wu, Zhenyu and Xu, Fangzhi and Wang, Yian and Sun, Qiushi and Jia, Chengyou and Cheng, Kanzhi and Ding, Zichen and Chen, Liheng and Liang, Paul Pu and others},
|
||||
journal={arXiv preprint arXiv:2410.23218},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</box>": 32019,
|
||||
"</img>": 32012,
|
||||
"</point>": 32021,
|
||||
"</quad>": 32015,
|
||||
"</ref>": 32017,
|
||||
"<IMG_CONTEXT>": 32013,
|
||||
"<box>": 32018,
|
||||
"<img>": 32011,
|
||||
"<point>": 32020,
|
||||
"<quad>": 32014,
|
||||
"<ref>": 32016,
|
||||
"<|assistant|>": 32001,
|
||||
"<|endoftext|>": 32000,
|
||||
"<|end|>": 32007,
|
||||
"<|placeholder1|>": 32002,
|
||||
"<|placeholder2|>": 32003,
|
||||
"<|placeholder3|>": 32004,
|
||||
"<|placeholder4|>": 32005,
|
||||
"<|placeholder5|>": 32008,
|
||||
"<|placeholder6|>": 32009,
|
||||
"<|system|>": 32006,
|
||||
"<|user|>": 32010
|
||||
}
|
||||
301
config.json
Normal file
301
config.json
Normal file
@@ -0,0 +1,301 @@
|
||||
{
|
||||
"_commit_hash": null,
|
||||
"_name_or_path": "OS-Atlas-Base-4B",
|
||||
"architectures": [
|
||||
"InternVLChatModel"
|
||||
],
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
|
||||
"AutoModel": "modeling_internvl_chat.InternVLChatModel",
|
||||
"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
|
||||
},
|
||||
"downsample_ratio": 0.5,
|
||||
"dynamic_image_size": true,
|
||||
"force_image_size": 448,
|
||||
"llm_config": {
|
||||
"_name_or_path": "./pretrained/Phi-3-mini-128k-instruct",
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"Phi3ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_phi3.Phi3Config",
|
||||
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
||||
},
|
||||
"bad_words_ids": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"bos_token_id": 1,
|
||||
"chunk_size_feed_forward": 0,
|
||||
"cross_attention_hidden_size": null,
|
||||
"decoder_start_token_id": null,
|
||||
"diversity_penalty": 0.0,
|
||||
"do_sample": false,
|
||||
"early_stopping": false,
|
||||
"embd_pdrop": 0.0,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"eos_token_id": 32000,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"finetuning_task": null,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"is_decoder": false,
|
||||
"is_encoder_decoder": false,
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"length_penalty": 1.0,
|
||||
"max_length": 20,
|
||||
"max_position_embeddings": 131072,
|
||||
"min_length": 0,
|
||||
"model_type": "phi3",
|
||||
"no_repeat_ngram_size": 0,
|
||||
"num_attention_heads": 32,
|
||||
"num_beam_groups": 1,
|
||||
"num_beams": 1,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"num_return_sequences": 1,
|
||||
"original_max_position_embeddings": 4096,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"output_scores": false,
|
||||
"pad_token_id": 32000,
|
||||
"prefix": null,
|
||||
"problem_type": null,
|
||||
"pruned_heads": {},
|
||||
"remove_invalid_values": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"resid_pdrop": 0.0,
|
||||
"return_dict": true,
|
||||
"return_dict_in_generate": false,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"long_factor": [
|
||||
1.0299999713897705,
|
||||
1.0499999523162842,
|
||||
1.0499999523162842,
|
||||
1.0799999237060547,
|
||||
1.2299998998641968,
|
||||
1.2299998998641968,
|
||||
1.2999999523162842,
|
||||
1.4499999284744263,
|
||||
1.5999999046325684,
|
||||
1.6499998569488525,
|
||||
1.8999998569488525,
|
||||
2.859999895095825,
|
||||
3.68999981880188,
|
||||
5.419999599456787,
|
||||
5.489999771118164,
|
||||
5.489999771118164,
|
||||
9.09000015258789,
|
||||
11.579999923706055,
|
||||
15.65999984741211,
|
||||
15.769999504089355,
|
||||
15.789999961853027,
|
||||
18.360000610351562,
|
||||
21.989999771118164,
|
||||
23.079999923706055,
|
||||
30.009998321533203,
|
||||
32.35000228881836,
|
||||
32.590003967285156,
|
||||
35.56000518798828,
|
||||
39.95000457763672,
|
||||
53.840003967285156,
|
||||
56.20000457763672,
|
||||
57.95000457763672,
|
||||
59.29000473022461,
|
||||
59.77000427246094,
|
||||
59.920005798339844,
|
||||
61.190006256103516,
|
||||
61.96000671386719,
|
||||
62.50000762939453,
|
||||
63.3700065612793,
|
||||
63.48000717163086,
|
||||
63.48000717163086,
|
||||
63.66000747680664,
|
||||
63.850006103515625,
|
||||
64.08000946044922,
|
||||
64.760009765625,
|
||||
64.80001068115234,
|
||||
64.81001281738281,
|
||||
64.81001281738281
|
||||
],
|
||||
"short_factor": [
|
||||
1.05,
|
||||
1.05,
|
||||
1.05,
|
||||
1.1,
|
||||
1.1,
|
||||
1.1500000000000001,
|
||||
1.2000000000000002,
|
||||
1.2500000000000002,
|
||||
1.3000000000000003,
|
||||
1.3500000000000003,
|
||||
1.5000000000000004,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.000000000000001,
|
||||
2.0500000000000007,
|
||||
2.0500000000000007,
|
||||
2.0500000000000007,
|
||||
2.1000000000000005,
|
||||
2.1000000000000005,
|
||||
2.1000000000000005,
|
||||
2.1500000000000004,
|
||||
2.1500000000000004,
|
||||
2.3499999999999996,
|
||||
2.549999999999999,
|
||||
2.5999999999999988,
|
||||
2.5999999999999988,
|
||||
2.7499999999999982,
|
||||
2.849999999999998,
|
||||
2.849999999999998,
|
||||
2.9499999999999975
|
||||
],
|
||||
"type": "su"
|
||||
},
|
||||
"rope_theta": 10000.0,
|
||||
"sep_token_id": null,
|
||||
"sliding_window": 262144,
|
||||
"suppress_tokens": null,
|
||||
"task_specific_params": null,
|
||||
"temperature": 1.0,
|
||||
"tf_legacy_loss": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": null,
|
||||
"top_k": 50,
|
||||
"top_p": null,
|
||||
"torch_dtype": "bfloat16",
|
||||
"torchscript": false,
|
||||
"transformers_version": "4.41.2",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": true,
|
||||
"use_cache": false,
|
||||
"vocab_size": 32022
|
||||
},
|
||||
"max_dynamic_patch": 6,
|
||||
"min_dynamic_patch": 1,
|
||||
"model_type": "internvl_chat",
|
||||
"pad2square": false,
|
||||
"ps_version": "v2",
|
||||
"select_layer": -1,
|
||||
"template": "phi3-chat",
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": null,
|
||||
"use_backbone_lora": 0,
|
||||
"use_llm_lora": 0,
|
||||
"use_thumbnail": true,
|
||||
"vision_config": {
|
||||
"_name_or_path": "",
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"InternVisionModel"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bad_words_ids": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"bos_token_id": null,
|
||||
"chunk_size_feed_forward": 0,
|
||||
"cross_attention_hidden_size": null,
|
||||
"decoder_start_token_id": null,
|
||||
"diversity_penalty": 0.0,
|
||||
"do_sample": false,
|
||||
"drop_path_rate": 0.1,
|
||||
"dropout": 0.0,
|
||||
"early_stopping": false,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"eos_token_id": null,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"finetuning_task": null,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 1024,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"image_size": 448,
|
||||
"initializer_factor": 1.0,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"is_decoder": false,
|
||||
"is_encoder_decoder": false,
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"layer_norm_eps": 1e-06,
|
||||
"length_penalty": 1.0,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"model_type": "intern_vit_6b",
|
||||
"no_repeat_ngram_size": 0,
|
||||
"norm_type": "layer_norm",
|
||||
"num_attention_heads": 16,
|
||||
"num_beam_groups": 1,
|
||||
"num_beams": 1,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 24,
|
||||
"num_return_sequences": 1,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"output_scores": false,
|
||||
"pad_token_id": null,
|
||||
"patch_size": 14,
|
||||
"prefix": null,
|
||||
"problem_type": null,
|
||||
"pruned_heads": {},
|
||||
"qk_normalization": false,
|
||||
"qkv_bias": true,
|
||||
"remove_invalid_values": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"return_dict": true,
|
||||
"return_dict_in_generate": false,
|
||||
"sep_token_id": null,
|
||||
"suppress_tokens": null,
|
||||
"task_specific_params": null,
|
||||
"temperature": 1.0,
|
||||
"tf_legacy_loss": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"tie_word_embeddings": true,
|
||||
"tokenizer_class": null,
|
||||
"top_k": 50,
|
||||
"top_p": null,
|
||||
"torch_dtype": "bfloat16",
|
||||
"torchscript": false,
|
||||
"transformers_version": "4.41.2",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": true,
|
||||
"use_flash_attn": true
|
||||
}
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}
|
||||
119
configuration_intern_vit.py
Normal file
119
configuration_intern_vit.py
Normal file
@@ -0,0 +1,119 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2023 OpenGVLab
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# --------------------------------------------------------
|
||||
import os
|
||||
from typing import Union
|
||||
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class InternVisionConfig(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
|
||||
instantiate a vision encoder according to the specified arguments, defining the model architecture.
|
||||
|
||||
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
||||
documentation from [`PretrainedConfig`] for more information.
|
||||
|
||||
Args:
|
||||
num_channels (`int`, *optional*, defaults to 3):
|
||||
Number of color channels in the input images (e.g., 3 for RGB).
|
||||
patch_size (`int`, *optional*, defaults to 14):
|
||||
The size (resolution) of each patch.
|
||||
image_size (`int`, *optional*, defaults to 224):
|
||||
The size (resolution) of each image.
|
||||
qkv_bias (`bool`, *optional*, defaults to `False`):
|
||||
Whether to add a bias to the queries and values in the self-attention layers.
|
||||
hidden_size (`int`, *optional*, defaults to 3200):
|
||||
Dimensionality of the encoder layers and the pooler layer.
|
||||
num_attention_heads (`int`, *optional*, defaults to 25):
|
||||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
intermediate_size (`int`, *optional*, defaults to 12800):
|
||||
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
|
||||
qk_normalization (`bool`, *optional*, defaults to `True`):
|
||||
Whether to normalize the queries and keys in the self-attention layers.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 48):
|
||||
Number of hidden layers in the Transformer encoder.
|
||||
use_flash_attn (`bool`, *optional*, defaults to `True`):
|
||||
Whether to use flash attention mechanism.
|
||||
hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
|
||||
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
|
||||
`"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
|
||||
layer_norm_eps (`float`, *optional*, defaults to 1e-6):
|
||||
The epsilon used by the layer normalization layers.
|
||||
dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
|
||||
drop_path_rate (`float`, *optional*, defaults to 0.0):
|
||||
Dropout rate for stochastic depth.
|
||||
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout ratio for the attention probabilities.
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
initializer_factor (`float`, *optional*, defaults to 0.1):
|
||||
A factor for layer scale.
|
||||
"""
|
||||
|
||||
model_type = 'intern_vit_6b'
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
num_channels=3,
|
||||
patch_size=14,
|
||||
image_size=224,
|
||||
qkv_bias=False,
|
||||
hidden_size=3200,
|
||||
num_attention_heads=25,
|
||||
intermediate_size=12800,
|
||||
qk_normalization=True,
|
||||
num_hidden_layers=48,
|
||||
use_flash_attn=True,
|
||||
hidden_act='gelu',
|
||||
norm_type='rms_norm',
|
||||
layer_norm_eps=1e-6,
|
||||
dropout=0.0,
|
||||
drop_path_rate=0.0,
|
||||
attention_dropout=0.0,
|
||||
initializer_range=0.02,
|
||||
initializer_factor=0.1,
|
||||
**kwargs,
|
||||
):
|
||||
super().__init__(**kwargs)
|
||||
|
||||
self.hidden_size = hidden_size
|
||||
self.intermediate_size = intermediate_size
|
||||
self.dropout = dropout
|
||||
self.drop_path_rate = drop_path_rate
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.num_channels = num_channels
|
||||
self.patch_size = patch_size
|
||||
self.image_size = image_size
|
||||
self.initializer_range = initializer_range
|
||||
self.initializer_factor = initializer_factor
|
||||
self.attention_dropout = attention_dropout
|
||||
self.layer_norm_eps = layer_norm_eps
|
||||
self.hidden_act = hidden_act
|
||||
self.norm_type = norm_type
|
||||
self.qkv_bias = qkv_bias
|
||||
self.qk_normalization = qk_normalization
|
||||
self.use_flash_attn = use_flash_attn
|
||||
|
||||
@classmethod
|
||||
def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
|
||||
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
|
||||
|
||||
if 'vision_config' in config_dict:
|
||||
config_dict = config_dict['vision_config']
|
||||
|
||||
if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
|
||||
logger.warning(
|
||||
f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
|
||||
f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
|
||||
)
|
||||
|
||||
return cls.from_dict(config_dict, **kwargs)
|
||||
99
configuration_internvl_chat.py
Normal file
99
configuration_internvl_chat.py
Normal file
@@ -0,0 +1,99 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2023 OpenGVLab
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# --------------------------------------------------------
|
||||
|
||||
import copy
|
||||
|
||||
from transformers import AutoConfig, LlamaConfig
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
from .configuration_intern_vit import InternVisionConfig
|
||||
from .configuration_phi3 import Phi3Config
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class InternVLChatConfig(PretrainedConfig):
|
||||
model_type = 'internvl_chat'
|
||||
is_composition = True
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vision_config=None,
|
||||
llm_config=None,
|
||||
use_backbone_lora=0,
|
||||
use_llm_lora=0,
|
||||
pad2square=False,
|
||||
select_layer=-1,
|
||||
force_image_size=None,
|
||||
downsample_ratio=0.5,
|
||||
template=None,
|
||||
dynamic_image_size=False,
|
||||
use_thumbnail=False,
|
||||
ps_version='v1',
|
||||
min_dynamic_patch=1,
|
||||
max_dynamic_patch=6,
|
||||
**kwargs):
|
||||
super().__init__(**kwargs)
|
||||
|
||||
if vision_config is None:
|
||||
vision_config = {}
|
||||
logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
|
||||
|
||||
if llm_config is None:
|
||||
llm_config = {}
|
||||
logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
|
||||
|
||||
self.vision_config = InternVisionConfig(**vision_config)
|
||||
if llm_config['architectures'][0] == 'LlamaForCausalLM':
|
||||
self.llm_config = LlamaConfig(**llm_config)
|
||||
elif llm_config['architectures'][0] == 'Phi3ForCausalLM':
|
||||
self.llm_config = Phi3Config(**llm_config)
|
||||
else:
|
||||
raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))
|
||||
self.use_backbone_lora = use_backbone_lora
|
||||
self.use_llm_lora = use_llm_lora
|
||||
self.pad2square = pad2square
|
||||
self.select_layer = select_layer
|
||||
self.force_image_size = force_image_size
|
||||
self.downsample_ratio = downsample_ratio
|
||||
self.template = template
|
||||
self.dynamic_image_size = dynamic_image_size
|
||||
self.use_thumbnail = use_thumbnail
|
||||
self.ps_version = ps_version # pixel shuffle version
|
||||
self.min_dynamic_patch = min_dynamic_patch
|
||||
self.max_dynamic_patch = max_dynamic_patch
|
||||
|
||||
logger.info(f'vision_select_layer: {self.select_layer}')
|
||||
logger.info(f'ps_version: {self.ps_version}')
|
||||
logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
|
||||
logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
|
||||
|
||||
def to_dict(self):
|
||||
"""
|
||||
Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
|
||||
|
||||
Returns:
|
||||
`Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
|
||||
"""
|
||||
output = copy.deepcopy(self.__dict__)
|
||||
output['vision_config'] = self.vision_config.to_dict()
|
||||
output['llm_config'] = self.llm_config.to_dict()
|
||||
output['model_type'] = self.__class__.model_type
|
||||
output['use_backbone_lora'] = self.use_backbone_lora
|
||||
output['use_llm_lora'] = self.use_llm_lora
|
||||
output['pad2square'] = self.pad2square
|
||||
output['select_layer'] = self.select_layer
|
||||
output['force_image_size'] = self.force_image_size
|
||||
output['downsample_ratio'] = self.downsample_ratio
|
||||
output['template'] = self.template
|
||||
output['dynamic_image_size'] = self.dynamic_image_size
|
||||
output['use_thumbnail'] = self.use_thumbnail
|
||||
output['ps_version'] = self.ps_version
|
||||
output['min_dynamic_patch'] = self.min_dynamic_patch
|
||||
output['max_dynamic_patch'] = self.max_dynamic_patch
|
||||
|
||||
return output
|
||||
211
configuration_phi3.py
Normal file
211
configuration_phi3.py
Normal file
@@ -0,0 +1,211 @@
|
||||
# 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 atd
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
""" Phi-3 model configuration"""
|
||||
|
||||
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
PHI3_PRETRAINED_CONFIG_ARCHIVE_MAP = {
|
||||
'microsoft/Phi-3-mini-4k-instruct': 'https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/resolve/main/config.json',
|
||||
'microsoft/Phi-3-mini-128k-instruct': 'https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/config.json',
|
||||
}
|
||||
|
||||
|
||||
class Phi3Config(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`Phi3Model`]. It is used to instantiate a Phi-3
|
||||
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
||||
defaults will yield a similar configuration to that of the
|
||||
[microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
|
||||
|
||||
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
||||
documentation from [`PretrainedConfig`] for more information.
|
||||
|
||||
Args:
|
||||
vocab_size (`int`, *optional*, defaults to 32064):
|
||||
Vocabulary size of the Phi-3 model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`Phi3Model`].
|
||||
hidden_size (`int`, *optional*, defaults to 3072):
|
||||
Dimension of the hidden representations.
|
||||
intermediate_size (`int`, *optional*, defaults to 8192):
|
||||
Dimension of the MLP representations.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 32):
|
||||
Number of hidden layers in the Transformer decoder.
|
||||
num_attention_heads (`int`, *optional*, defaults to 32):
|
||||
Number of attention heads for each attention layer in the Transformer decoder.
|
||||
num_key_value_heads (`int`, *optional*):
|
||||
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
||||
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
||||
`num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
||||
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
||||
by meanpooling all the original heads within that group. For more details checkout [this
|
||||
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
|
||||
`num_attention_heads`.
|
||||
resid_pdrop (`float`, *optional*, defaults to 0.0):
|
||||
Dropout probability for mlp outputs.
|
||||
embd_pdrop (`int`, *optional*, defaults to 0.0):
|
||||
The dropout ratio for the embeddings.
|
||||
attention_dropout (`float`, *optional*, defaults to 0.0):
|
||||
The dropout ratio after computing the attention scores.
|
||||
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
||||
The non-linear activation function (function or string) in the decoder.
|
||||
max_position_embeddings (`int`, *optional*, defaults to 4096):
|
||||
The maximum sequence length that this model might ever be used with.
|
||||
original_max_position_embeddings (`int`, *optional*, defaults to 4096):
|
||||
The maximum sequence length that this model was trained with. This is used to determine the size of the
|
||||
original RoPE embeddings when using long scaling.
|
||||
initializer_range (`float`, *optional*, defaults to 0.02):
|
||||
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
||||
rms_norm_eps (`float`, *optional*, defaults to 1e-05):
|
||||
The epsilon value used for the RMSNorm.
|
||||
use_cache (`bool`, *optional*, defaults to `True`):
|
||||
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
||||
relevant if `config.is_decoder=True`. Whether to tie weight embeddings or not.
|
||||
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
||||
Whether to tie weight embeddings
|
||||
rope_theta (`float`, *optional*, defaults to 10000.0):
|
||||
The base period of the RoPE embeddings.
|
||||
rope_scaling (`dict`, *optional*):
|
||||
The scaling strategy for the RoPE embeddings. If `None`, no scaling is applied. If a dictionary, it must
|
||||
contain the following keys: `type`, `short_factor` and `long_factor`. The `type` must be 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.
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
>>> from transformers import Phi3Model, Phi3Config
|
||||
|
||||
>>> # Initializing a Phi-3 style configuration
|
||||
>>> configuration = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
|
||||
|
||||
>>> # Initializing a model from the configuration
|
||||
>>> model = Phi3Model(configuration)
|
||||
|
||||
>>> # Accessing the model configuration
|
||||
>>> configuration = model.config
|
||||
```"""
|
||||
|
||||
model_type = 'phi3'
|
||||
keys_to_ignore_at_inference = ['past_key_values']
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_size=32064,
|
||||
hidden_size=3072,
|
||||
intermediate_size=8192,
|
||||
num_hidden_layers=32,
|
||||
num_attention_heads=32,
|
||||
num_key_value_heads=None,
|
||||
resid_pdrop=0.0,
|
||||
embd_pdrop=0.0,
|
||||
attention_dropout=0.0,
|
||||
hidden_act='silu',
|
||||
max_position_embeddings=4096,
|
||||
original_max_position_embeddings=4096,
|
||||
initializer_range=0.02,
|
||||
rms_norm_eps=1e-5,
|
||||
use_cache=True,
|
||||
tie_word_embeddings=False,
|
||||
rope_theta=10000.0,
|
||||
rope_scaling=None,
|
||||
bos_token_id=1,
|
||||
eos_token_id=32000,
|
||||
pad_token_id=32000,
|
||||
sliding_window=None,
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.intermediate_size = intermediate_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
|
||||
if num_key_value_heads is None:
|
||||
num_key_value_heads = num_attention_heads
|
||||
|
||||
self.num_key_value_heads = num_key_value_heads
|
||||
self.resid_pdrop = resid_pdrop
|
||||
self.embd_pdrop = embd_pdrop
|
||||
self.attention_dropout = attention_dropout
|
||||
self.hidden_act = hidden_act
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.original_max_position_embeddings = original_max_position_embeddings
|
||||
self.initializer_range = initializer_range
|
||||
self.rms_norm_eps = rms_norm_eps
|
||||
self.use_cache = use_cache
|
||||
self.rope_theta = rope_theta
|
||||
self.rope_scaling = rope_scaling
|
||||
self._rope_scaling_validation()
|
||||
self.sliding_window = sliding_window
|
||||
|
||||
super().__init__(
|
||||
bos_token_id=bos_token_id,
|
||||
eos_token_id=eos_token_id,
|
||||
pad_token_id=pad_token_id,
|
||||
tie_word_embeddings=tie_word_embeddings,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
def _rope_scaling_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)}"
|
||||
)
|
||||
383
conversation.py
Normal file
383
conversation.py
Normal file
@@ -0,0 +1,383 @@
|
||||
"""
|
||||
Conversation prompt templates.
|
||||
|
||||
We kindly request that you import fastchat instead of copying this file if you wish to use it.
|
||||
If you have any changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
|
||||
"""
|
||||
|
||||
import dataclasses
|
||||
from enum import IntEnum, auto
|
||||
from typing import Any, Dict, List, Tuple, Union
|
||||
|
||||
|
||||
class SeparatorStyle(IntEnum):
|
||||
"""Separator styles."""
|
||||
|
||||
ADD_COLON_SINGLE = auto()
|
||||
ADD_COLON_TWO = auto()
|
||||
ADD_COLON_SPACE_SINGLE = auto()
|
||||
NO_COLON_SINGLE = auto()
|
||||
NO_COLON_TWO = auto()
|
||||
ADD_NEW_LINE_SINGLE = auto()
|
||||
LLAMA2 = auto()
|
||||
CHATGLM = auto()
|
||||
CHATML = auto()
|
||||
CHATINTERN = auto()
|
||||
DOLLY = auto()
|
||||
RWKV = auto()
|
||||
PHOENIX = auto()
|
||||
ROBIN = auto()
|
||||
FALCON_CHAT = auto()
|
||||
CHATGLM3 = auto()
|
||||
INTERNVL_ZH = auto()
|
||||
MPT = auto()
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
class Conversation:
|
||||
"""A class that manages prompt templates and keeps all conversation history."""
|
||||
|
||||
# The name of this template
|
||||
name: str
|
||||
# The template of the system prompt
|
||||
system_template: str = '{system_message}'
|
||||
# The system message
|
||||
system_message: str = ''
|
||||
# The names of two roles
|
||||
roles: Tuple[str] = ('USER', 'ASSISTANT')
|
||||
# All messages. Each item is (role, message).
|
||||
messages: List[List[str]] = ()
|
||||
# The number of few shot examples
|
||||
offset: int = 0
|
||||
# The separator style and configurations
|
||||
sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
|
||||
sep: str = '\n'
|
||||
sep2: str = None
|
||||
# Stop criteria (the default one is EOS token)
|
||||
stop_str: Union[str, List[str]] = None
|
||||
# Stops generation if meeting any token in this list
|
||||
stop_token_ids: List[int] = None
|
||||
|
||||
def get_prompt(self) -> str:
|
||||
"""Get the prompt for generation."""
|
||||
system_prompt = self.system_template.format(system_message=self.system_message)
|
||||
if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
|
||||
ret = system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ': ' + message + self.sep
|
||||
else:
|
||||
ret += role + ':'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = system_prompt + seps[0]
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += role + ': ' + message + seps[i % 2]
|
||||
else:
|
||||
ret += role + ':'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
|
||||
ret = system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ': ' + message + self.sep
|
||||
else:
|
||||
ret += role + ': ' # must be end with a space
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
|
||||
ret = '' if system_prompt == '' else system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + '\n' + message + self.sep
|
||||
else:
|
||||
ret += role + '\n'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
|
||||
ret = system_prompt
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + message + self.sep
|
||||
else:
|
||||
ret += role
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = system_prompt
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += role + message + seps[i % 2]
|
||||
else:
|
||||
ret += role
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.RWKV:
|
||||
ret = system_prompt
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += (
|
||||
role
|
||||
+ ': '
|
||||
+ message.replace('\r\n', '\n').replace('\n\n', '\n')
|
||||
)
|
||||
ret += '\n\n'
|
||||
else:
|
||||
ret += role + ':'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.LLAMA2:
|
||||
seps = [self.sep, self.sep2]
|
||||
if self.system_message:
|
||||
ret = system_prompt
|
||||
else:
|
||||
ret = '[INST] '
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
tag = self.roles[i % 2]
|
||||
if message:
|
||||
if i == 0:
|
||||
ret += message + ' '
|
||||
else:
|
||||
ret += tag + ' ' + message + seps[i % 2]
|
||||
else:
|
||||
ret += tag
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.CHATGLM:
|
||||
# source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
|
||||
# source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
|
||||
round_add_n = 1 if self.name == 'chatglm2' else 0
|
||||
if system_prompt:
|
||||
ret = system_prompt + self.sep
|
||||
else:
|
||||
ret = ''
|
||||
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if i % 2 == 0:
|
||||
ret += f'[Round {i//2 + round_add_n}]{self.sep}'
|
||||
|
||||
if message:
|
||||
ret += f'{role}：{message}{self.sep}'
|
||||
else:
|
||||
ret += f'{role}：'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.CHATML:
|
||||
ret = '' if system_prompt == '' else system_prompt + self.sep + '\n'
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + '\n' + message + self.sep + '\n'
|
||||
else:
|
||||
ret += role + '\n'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.CHATGLM3:
|
||||
ret = ''
|
||||
if self.system_message:
|
||||
ret += system_prompt
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + '\n' + ' ' + message
|
||||
else:
|
||||
ret += role
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.CHATINTERN:
|
||||
# source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = system_prompt
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
# if i % 2 == 0:
|
||||
# ret += "<s>"
|
||||
if message:
|
||||
ret += role + ':' + message + seps[i % 2] + '\n'
|
||||
else:
|
||||
ret += role + ':'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.DOLLY:
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = system_prompt
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += role + ':\n' + message + seps[i % 2]
|
||||
if i % 2 == 1:
|
||||
ret += '\n\n'
|
||||
else:
|
||||
ret += role + ':\n'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.PHOENIX:
|
||||
ret = system_prompt
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ': ' + '<s>' + message + '</s>'
|
||||
else:
|
||||
ret += role + ': ' + '<s>'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.ROBIN:
|
||||
ret = system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ':\n' + message + self.sep
|
||||
else:
|
||||
ret += role + ':\n'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.FALCON_CHAT:
|
||||
ret = ''
|
||||
if self.system_message:
|
||||
ret += system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
ret += role + ': ' + message + self.sep
|
||||
else:
|
||||
ret += role + ':'
|
||||
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.INTERNVL_ZH:
|
||||
seps = [self.sep, self.sep2]
|
||||
ret = self.system_message + seps[0]
|
||||
for i, (role, message) in enumerate(self.messages):
|
||||
if message:
|
||||
ret += role + ': ' + message + seps[i % 2]
|
||||
else:
|
||||
ret += role + ':'
|
||||
return ret
|
||||
elif self.sep_style == SeparatorStyle.MPT:
|
||||
ret = system_prompt + self.sep
|
||||
for role, message in self.messages:
|
||||
if message:
|
||||
if type(message) is tuple:
|
||||
message, _, _ = message
|
||||
ret += role + message + self.sep
|
||||
else:
|
||||
ret += role
|
||||
return ret
|
||||
else:
|
||||
raise ValueError(f'Invalid style: {self.sep_style}')
|
||||
|
||||
def set_system_message(self, system_message: str):
|
||||
"""Set the system message."""
|
||||
self.system_message = system_message
|
||||
|
||||
def append_message(self, role: str, message: str):
|
||||
"""Append a new message."""
|
||||
self.messages.append([role, message])
|
||||
|
||||
def update_last_message(self, message: str):
|
||||
"""Update the last output.
|
||||
|
||||
The last message is typically set to be None when constructing the prompt,
|
||||
so we need to update it in-place after getting the response from a model.
|
||||
"""
|
||||
self.messages[-1][1] = message
|
||||
|
||||
def to_gradio_chatbot(self):
|
||||
"""Convert the conversation to gradio chatbot format."""
|
||||
ret = []
|
||||
for i, (role, msg) in enumerate(self.messages[self.offset :]):
|
||||
if i % 2 == 0:
|
||||
ret.append([msg, None])
|
||||
else:
|
||||
ret[-1][-1] = msg
|
||||
return ret
|
||||
|
||||
def to_openai_api_messages(self):
|
||||
"""Convert the conversation to OpenAI chat completion format."""
|
||||
ret = [{'role': 'system', 'content': self.system_message}]
|
||||
|
||||
for i, (_, msg) in enumerate(self.messages[self.offset :]):
|
||||
if i % 2 == 0:
|
||||
ret.append({'role': 'user', 'content': msg})
|
||||
else:
|
||||
if msg is not None:
|
||||
ret.append({'role': 'assistant', 'content': msg})
|
||||
return ret
|
||||
|
||||
def copy(self):
|
||||
return Conversation(
|
||||
name=self.name,
|
||||
system_template=self.system_template,
|
||||
system_message=self.system_message,
|
||||
roles=self.roles,
|
||||
messages=[[x, y] for x, y in self.messages],
|
||||
offset=self.offset,
|
||||
sep_style=self.sep_style,
|
||||
sep=self.sep,
|
||||
sep2=self.sep2,
|
||||
stop_str=self.stop_str,
|
||||
stop_token_ids=self.stop_token_ids,
|
||||
)
|
||||
|
||||
def dict(self):
|
||||
return {
|
||||
'template_name': self.name,
|
||||
'system_message': self.system_message,
|
||||
'roles': self.roles,
|
||||
'messages': self.messages,
|
||||
'offset': self.offset,
|
||||
}
|
||||
|
||||
|
||||
# A global registry for all conversation templates
|
||||
conv_templates: Dict[str, Conversation] = {}
|
||||
|
||||
|
||||
def register_conv_template(template: Conversation, override: bool = False):
|
||||
"""Register a new conversation template."""
|
||||
if not override:
|
||||
assert (
|
||||
template.name not in conv_templates
|
||||
), f'{template.name} has been registered.'
|
||||
|
||||
conv_templates[template.name] = template
|
||||
|
||||
|
||||
def get_conv_template(name: str) -> Conversation:
|
||||
"""Get a conversation template."""
|
||||
return conv_templates[name].copy()
|
||||
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='Hermes-2',
|
||||
system_template='<|im_start|>system\n{system_message}',
|
||||
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
|
||||
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
|
||||
sep_style=SeparatorStyle.MPT,
|
||||
sep='<|im_end|>',
|
||||
stop_token_ids=[
|
||||
2,
|
||||
6,
|
||||
7,
|
||||
8,
|
||||
], # "<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|im_sep|>"
|
||||
stop_str='<|endoftext|>',
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='internlm2-chat',
|
||||
system_template='<|im_start|>system\n{system_message}',
|
||||
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
|
||||
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
|
||||
sep_style=SeparatorStyle.MPT,
|
||||
sep='<|im_end|>',
|
||||
stop_token_ids=[
|
||||
2,
|
||||
92543,
|
||||
92542
|
||||
]
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='phi3-chat',
|
||||
system_template='<|system|>\n{system_message}',
|
||||
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
|
||||
roles=('<|user|>\n', '<|assistant|>\n'),
|
||||
sep_style=SeparatorStyle.MPT,
|
||||
sep='<|end|>',
|
||||
stop_token_ids=[
|
||||
2,
|
||||
32000,
|
||||
32007
|
||||
]
|
||||
)
|
||||
)
|
||||
4
generation_config.json
Normal file
4
generation_config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"transformers_version": "4.41.2"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27c90197ec6a0a21c6152c6a7012338aac2178e9867da41fe5d173af2dab26d7
|
||||
size 4957404464
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d31d0c07e0877880611642340b866529d38da3daed7427bb632c6c8efeb89690
|
||||
size 3336398152
|
||||
548
model.safetensors.index.json
Normal file
548
model.safetensors.index.json
Normal file
@@ -0,0 +1,548 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8293736448
|
||||
},
|
||||
"weight_map": {
|
||||
"language_model.lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
||||
"mlp1.0.bias": "model-00002-of-00002.safetensors",
|
||||
"mlp1.0.weight": "model-00002-of-00002.safetensors",
|
||||
"mlp1.1.bias": "model-00002-of-00002.safetensors",
|
||||
"mlp1.1.weight": "model-00002-of-00002.safetensors",
|
||||
"mlp1.3.bias": "model-00002-of-00002.safetensors",
|
||||
"mlp1.3.weight": "model-00002-of-00002.safetensors",
|
||||
"vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
|
||||
"vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.embeddings.position_embedding": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.ls1": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.ls2": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00002.safetensors",
|
||||
"vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
434
modeling_intern_vit.py
Normal file
434
modeling_intern_vit.py
Normal file
@@ -0,0 +1,434 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2023 OpenGVLab
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# --------------------------------------------------------
|
||||
from typing import Optional, Tuple, Union
|
||||
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
import torch.utils.checkpoint
|
||||
from einops import rearrange
|
||||
from timm.models.layers import DropPath
|
||||
from torch import nn
|
||||
from transformers.activations import ACT2FN
|
||||
from transformers.modeling_outputs import (BaseModelOutput,
|
||||
BaseModelOutputWithPooling)
|
||||
from transformers.modeling_utils import PreTrainedModel
|
||||
from transformers.utils import logging
|
||||
|
||||
from .configuration_intern_vit import InternVisionConfig
|
||||
|
||||
try:
|
||||
try: # v1
|
||||
from flash_attn.flash_attn_interface import \
|
||||
flash_attn_unpadded_qkvpacked_func
|
||||
except: # v2
|
||||
from flash_attn.flash_attn_interface import \
|
||||
flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
|
||||
|
||||
from flash_attn.bert_padding import pad_input, unpad_input
|
||||
|
||||
has_flash_attn = True
|
||||
except:
|
||||
print('FlashAttention is not installed.')
|
||||
has_flash_attn = False
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class FlashAttention(nn.Module):
|
||||
"""Implement the scaled dot product attention with softmax.
|
||||
Arguments
|
||||
---------
|
||||
softmax_scale: The temperature to use for the softmax attention.
|
||||
(default: 1/sqrt(d_keys) where d_keys is computed at
|
||||
runtime)
|
||||
attention_dropout: The dropout rate to apply to the attention
|
||||
(default: 0.0)
|
||||
"""
|
||||
|
||||
def __init__(self, softmax_scale=None, attention_dropout=0.0, device=None, dtype=None):
|
||||
super().__init__()
|
||||
self.softmax_scale = softmax_scale
|
||||
self.dropout_p = attention_dropout
|
||||
|
||||
def forward(self, qkv, key_padding_mask=None, causal=False, cu_seqlens=None,
|
||||
max_s=None, need_weights=False):
|
||||
"""Implements the multihead softmax attention.
|
||||
Arguments
|
||||
---------
|
||||
qkv: The tensor containing the query, key, and value. (B, S, 3, H, D) if key_padding_mask is None
|
||||
if unpadded: (nnz, 3, h, d)
|
||||
key_padding_mask: a bool tensor of shape (B, S)
|
||||
"""
|
||||
assert not need_weights
|
||||
assert qkv.dtype in [torch.float16, torch.bfloat16]
|
||||
assert qkv.is_cuda
|
||||
|
||||
if cu_seqlens is None:
|
||||
batch_size = qkv.shape[0]
|
||||
seqlen = qkv.shape[1]
|
||||
if key_padding_mask is None:
|
||||
qkv = rearrange(qkv, 'b s ... -> (b s) ...')
|
||||
max_s = seqlen
|
||||
cu_seqlens = torch.arange(0, (batch_size + 1) * seqlen, step=seqlen, dtype=torch.int32,
|
||||
device=qkv.device)
|
||||
output = flash_attn_unpadded_qkvpacked_func(
|
||||
qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
|
||||
softmax_scale=self.softmax_scale, causal=causal
|
||||
)
|
||||
output = rearrange(output, '(b s) ... -> b s ...', b=batch_size)
|
||||
else:
|
||||
nheads = qkv.shape[-2]
|
||||
x = rearrange(qkv, 'b s three h d -> b s (three h d)')
|
||||
x_unpad, indices, cu_seqlens, max_s = unpad_input(x, key_padding_mask)
|
||||
x_unpad = rearrange(x_unpad, 'nnz (three h d) -> nnz three h d', three=3, h=nheads)
|
||||
output_unpad = flash_attn_unpadded_qkvpacked_func(
|
||||
x_unpad, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
|
||||
softmax_scale=self.softmax_scale, causal=causal
|
||||
)
|
||||
output = rearrange(pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'),
|
||||
indices, batch_size, seqlen),
|
||||
'b s (h d) -> b s h d', h=nheads)
|
||||
else:
|
||||
assert max_s is not None
|
||||
output = flash_attn_unpadded_qkvpacked_func(
|
||||
qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
|
||||
softmax_scale=self.softmax_scale, causal=causal
|
||||
)
|
||||
|
||||
return output, None
|
||||
|
||||
|
||||
class InternRMSNorm(nn.Module):
|
||||
def __init__(self, hidden_size, eps=1e-6):
|
||||
super().__init__()
|
||||
self.weight = nn.Parameter(torch.ones(hidden_size))
|
||||
self.variance_epsilon = eps
|
||||
|
||||
def forward(self, hidden_states):
|
||||
input_dtype = hidden_states.dtype
|
||||
hidden_states = hidden_states.to(torch.float32)
|
||||
variance = hidden_states.pow(2).mean(-1, keepdim=True)
|
||||
hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
|
||||
return self.weight * hidden_states.to(input_dtype)
|
||||
|
||||
|
||||
try:
|
||||
from apex.normalization import FusedRMSNorm
|
||||
|
||||
InternRMSNorm = FusedRMSNorm # noqa
|
||||
|
||||
logger.info('Discovered apex.normalization.FusedRMSNorm - will use it instead of InternRMSNorm')
|
||||
except ImportError:
|
||||
# using the normal InternRMSNorm
|
||||
pass
|
||||
except Exception:
|
||||
logger.warning('discovered apex but it failed to load, falling back to InternRMSNorm')
|
||||
pass
|
||||
|
||||
|
||||
NORM2FN = {
|
||||
'rms_norm': InternRMSNorm,
|
||||
'layer_norm': nn.LayerNorm,
|
||||
}
|
||||
|
||||
|
||||
class InternVisionEmbeddings(nn.Module):
|
||||
def __init__(self, config: InternVisionConfig):
|
||||
super().__init__()
|
||||
self.config = config
|
||||
self.embed_dim = config.hidden_size
|
||||
self.image_size = config.image_size
|
||||
self.patch_size = config.patch_size
|
||||
|
||||
self.class_embedding = nn.Parameter(
|
||||
torch.randn(1, 1, self.embed_dim),
|
||||
)
|
||||
|
||||
self.patch_embedding = nn.Conv2d(
|
||||
in_channels=3, out_channels=self.embed_dim, kernel_size=self.patch_size, stride=self.patch_size
|
||||
)
|
||||
|
||||
self.num_patches = (self.image_size // self.patch_size) ** 2
|
||||
self.num_positions = self.num_patches + 1
|
||||
|
||||
self.position_embedding = nn.Parameter(torch.randn(1, self.num_positions, self.embed_dim))
|
||||
|
||||
def _get_pos_embed(self, pos_embed, H, W):
|
||||
target_dtype = pos_embed.dtype
|
||||
pos_embed = pos_embed.float().reshape(
|
||||
1, self.image_size // self.patch_size, self.image_size // self.patch_size, -1).permute(0, 3, 1, 2)
|
||||
pos_embed = F.interpolate(pos_embed, size=(H, W), mode='bicubic', align_corners=False). \
|
||||
reshape(1, -1, H * W).permute(0, 2, 1).to(target_dtype)
|
||||
return pos_embed
|
||||
|
||||
def forward(self, pixel_values: torch.FloatTensor) -> torch.Tensor:
|
||||
target_dtype = self.patch_embedding.weight.dtype
|
||||
patch_embeds = self.patch_embedding(pixel_values) # shape = [*, channel, width, height]
|
||||
batch_size, _, height, width = patch_embeds.shape
|
||||
patch_embeds = patch_embeds.flatten(2).transpose(1, 2)
|
||||
class_embeds = self.class_embedding.expand(batch_size, 1, -1).to(target_dtype)
|
||||
embeddings = torch.cat([class_embeds, patch_embeds], dim=1)
|
||||
position_embedding = torch.cat([
|
||||
self.position_embedding[:, :1, :],
|
||||
self._get_pos_embed(self.position_embedding[:, 1:, :], height, width)
|
||||
], dim=1)
|
||||
embeddings = embeddings + position_embedding.to(target_dtype)
|
||||
return embeddings
|
||||
|
||||
|
||||
class InternAttention(nn.Module):
|
||||
"""Multi-headed attention from 'Attention Is All You Need' paper"""
|
||||
|
||||
def __init__(self, config: InternVisionConfig):
|
||||
super().__init__()
|
||||
self.config = config
|
||||
self.embed_dim = config.hidden_size
|
||||
self.num_heads = config.num_attention_heads
|
||||
self.use_flash_attn = config.use_flash_attn and has_flash_attn
|
||||
if config.use_flash_attn and not has_flash_attn:
|
||||
print('Warning: Flash Attention is not available, use_flash_attn is set to False.')
|
||||
self.head_dim = self.embed_dim // self.num_heads
|
||||
if self.head_dim * self.num_heads != self.embed_dim:
|
||||
raise ValueError(
|
||||
f'embed_dim must be divisible by num_heads (got `embed_dim`: {self.embed_dim} and `num_heads`:'
|
||||
f' {self.num_heads}).'
|
||||
)
|
||||
|
||||
self.scale = self.head_dim ** -0.5
|
||||
self.qkv = nn.Linear(self.embed_dim, 3 * self.embed_dim, bias=config.qkv_bias)
|
||||
self.attn_drop = nn.Dropout(config.attention_dropout)
|
||||
self.proj_drop = nn.Dropout(config.dropout)
|
||||
|
||||
self.qk_normalization = config.qk_normalization
|
||||
|
||||
if self.qk_normalization:
|
||||
self.q_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
|
||||
self.k_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
|
||||
|
||||
if self.use_flash_attn:
|
||||
self.inner_attn = FlashAttention(attention_dropout=config.attention_dropout)
|
||||
self.proj = nn.Linear(self.embed_dim, self.embed_dim)
|
||||
|
||||
def _naive_attn(self, x):
|
||||
B, N, C = x.shape
|
||||
qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
|
||||
q, k, v = qkv.unbind(0) # make torchscript happy (cannot use tensor as tuple)
|
||||
|
||||
if self.qk_normalization:
|
||||
B_, H_, N_, D_ = q.shape
|
||||
q = self.q_norm(q.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
|
||||
k = self.k_norm(k.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
|
||||
|
||||
attn = ((q * self.scale) @ k.transpose(-2, -1))
|
||||
attn = attn.softmax(dim=-1)
|
||||
attn = self.attn_drop(attn)
|
||||
|
||||
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
|
||||
x = self.proj(x)
|
||||
x = self.proj_drop(x)
|
||||
return x
|
||||
|
||||
def _flash_attn(self, x, key_padding_mask=None, need_weights=False):
|
||||
qkv = self.qkv(x)
|
||||
qkv = rearrange(qkv, 'b s (three h d) -> b s three h d', three=3, h=self.num_heads)
|
||||
|
||||
if self.qk_normalization:
|
||||
q, k, v = qkv.unbind(2)
|
||||
q = self.q_norm(q.flatten(-2, -1)).view(q.shape)
|
||||
k = self.k_norm(k.flatten(-2, -1)).view(k.shape)
|
||||
qkv = torch.stack([q, k, v], dim=2)
|
||||
|
||||
context, _ = self.inner_attn(
|
||||
qkv, key_padding_mask=key_padding_mask, need_weights=need_weights, causal=False
|
||||
)
|
||||
outs = self.proj(rearrange(context, 'b s h d -> b s (h d)'))
|
||||
outs = self.proj_drop(outs)
|
||||
return outs
|
||||
|
||||
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
|
||||
x = self._naive_attn(hidden_states) if not self.use_flash_attn else self._flash_attn(hidden_states)
|
||||
return x
|
||||
|
||||
|
||||
class InternMLP(nn.Module):
|
||||
def __init__(self, config: InternVisionConfig):
|
||||
super().__init__()
|
||||
self.config = config
|
||||
self.act = ACT2FN[config.hidden_act]
|
||||
self.fc1 = nn.Linear(config.hidden_size, config.intermediate_size)
|
||||
self.fc2 = nn.Linear(config.intermediate_size, config.hidden_size)
|
||||
|
||||
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
|
||||
hidden_states = self.fc1(hidden_states)
|
||||
hidden_states = self.act(hidden_states)
|
||||
hidden_states = self.fc2(hidden_states)
|
||||
return hidden_states
|
||||
|
||||
|
||||
class InternVisionEncoderLayer(nn.Module):
|
||||
def __init__(self, config: InternVisionConfig, drop_path_rate: float):
|
||||
super().__init__()
|
||||
self.embed_dim = config.hidden_size
|
||||
self.intermediate_size = config.intermediate_size
|
||||
self.norm_type = config.norm_type
|
||||
|
||||
self.attn = InternAttention(config)
|
||||
self.mlp = InternMLP(config)
|
||||
self.norm1 = NORM2FN[self.norm_type](self.embed_dim, eps=config.layer_norm_eps)
|
||||
self.norm2 = NORM2FN[self.norm_type](self.embed_dim, eps=config.layer_norm_eps)
|
||||
|
||||
self.ls1 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
|
||||
self.ls2 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
|
||||
self.drop_path1 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
|
||||
self.drop_path2 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
|
||||
|
||||
def forward(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor], Optional[Tuple[torch.FloatTensor]]]:
|
||||
"""
|
||||
Args:
|
||||
hidden_states (`Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]`): input to the layer of shape `(batch, seq_len, embed_dim)`
|
||||
"""
|
||||
hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states)) * self.ls1)
|
||||
|
||||
hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states)) * self.ls2)
|
||||
|
||||
return hidden_states
|
||||
|
||||
|
||||
class InternVisionEncoder(nn.Module):
|
||||
"""
|
||||
Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
|
||||
[`InternEncoderLayer`].
|
||||
|
||||
Args:
|
||||
config (`InternConfig`):
|
||||
The corresponding vision configuration for the `InternEncoder`.
|
||||
"""
|
||||
|
||||
def __init__(self, config: InternVisionConfig):
|
||||
super().__init__()
|
||||
self.config = config
|
||||
# stochastic depth decay rule
|
||||
dpr = [x.item() for x in torch.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
|
||||
self.layers = nn.ModuleList([
|
||||
InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
|
||||
self.gradient_checkpointing = True
|
||||
|
||||
def forward(
|
||||
self,
|
||||
inputs_embeds,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, BaseModelOutput]:
|
||||
r"""
|
||||
Args:
|
||||
inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
|
||||
Embedded representation of the inputs. Should be float, not int tokens.
|
||||
output_hidden_states (`bool`, *optional*):
|
||||
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
|
||||
for more detail.
|
||||
return_dict (`bool`, *optional*):
|
||||
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
|
||||
"""
|
||||
output_hidden_states = (
|
||||
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
|
||||
)
|
||||
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
||||
|
||||
encoder_states = () if output_hidden_states else None
|
||||
hidden_states = inputs_embeds
|
||||
|
||||
for idx, encoder_layer in enumerate(self.layers):
|
||||
if output_hidden_states:
|
||||
encoder_states = encoder_states + (hidden_states,)
|
||||
if self.gradient_checkpointing and self.training:
|
||||
layer_outputs = torch.utils.checkpoint.checkpoint(
|
||||
encoder_layer,
|
||||
hidden_states)
|
||||
else:
|
||||
layer_outputs = encoder_layer(
|
||||
hidden_states,
|
||||
)
|
||||
hidden_states = layer_outputs
|
||||
|
||||
if output_hidden_states:
|
||||
encoder_states = encoder_states + (hidden_states,)
|
||||
|
||||
if not return_dict:
|
||||
return tuple(v for v in [hidden_states, encoder_states] if v is not None)
|
||||
return BaseModelOutput(
|
||||
last_hidden_state=hidden_states, hidden_states=encoder_states
|
||||
)
|
||||
|
||||
|
||||
class InternVisionModel(PreTrainedModel):
|
||||
main_input_name = 'pixel_values'
|
||||
config_class = InternVisionConfig
|
||||
_no_split_modules = ['InternVisionEncoderLayer']
|
||||
|
||||
def __init__(self, config: InternVisionConfig):
|
||||
super().__init__(config)
|
||||
self.config = config
|
||||
|
||||
self.embeddings = InternVisionEmbeddings(config)
|
||||
self.encoder = InternVisionEncoder(config)
|
||||
|
||||
def resize_pos_embeddings(self, old_size, new_size, patch_size):
|
||||
pos_emb = self.embeddings.position_embedding
|
||||
_, num_positions, embed_dim = pos_emb.shape
|
||||
cls_emb = pos_emb[:, :1, :]
|
||||
pos_emb = pos_emb[:, 1:, :].reshape(1, old_size // patch_size, old_size // patch_size, -1).permute(0, 3, 1, 2)
|
||||
pos_emb = F.interpolate(pos_emb.float(), size=new_size // patch_size, mode='bicubic', align_corners=False)
|
||||
pos_emb = pos_emb.to(cls_emb.dtype).reshape(1, embed_dim, -1).permute(0, 2, 1)
|
||||
pos_emb = torch.cat([cls_emb, pos_emb], dim=1)
|
||||
self.embeddings.position_embedding = nn.Parameter(pos_emb)
|
||||
self.embeddings.image_size = new_size
|
||||
logger.info('Resized position embeddings from {} to {}'.format(old_size, new_size))
|
||||
|
||||
def get_input_embeddings(self):
|
||||
return self.embeddings
|
||||
|
||||
def forward(
|
||||
self,
|
||||
pixel_values: Optional[torch.FloatTensor] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
pixel_embeds: Optional[torch.FloatTensor] = None,
|
||||
) -> Union[Tuple, BaseModelOutputWithPooling]:
|
||||
output_hidden_states = (
|
||||
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
|
||||
)
|
||||
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
||||
|
||||
if pixel_values is None and pixel_embeds is None:
|
||||
raise ValueError('You have to specify pixel_values or pixel_embeds')
|
||||
|
||||
if pixel_embeds is not None:
|
||||
hidden_states = pixel_embeds
|
||||
else:
|
||||
if len(pixel_values.shape) == 4:
|
||||
hidden_states = self.embeddings(pixel_values)
|
||||
else:
|
||||
raise ValueError(f'wrong pixel_values size: {pixel_values.shape}')
|
||||
encoder_outputs = self.encoder(
|
||||
inputs_embeds=hidden_states,
|
||||
output_hidden_states=output_hidden_states,
|
||||
return_dict=return_dict,
|
||||
)
|
||||
last_hidden_state = encoder_outputs.last_hidden_state
|
||||
pooled_output = last_hidden_state[:, 0, :]
|
||||
|
||||
if not return_dict:
|
||||
return (last_hidden_state, pooled_output) + encoder_outputs[1:]
|
||||
|
||||
return BaseModelOutputWithPooling(
|
||||
last_hidden_state=last_hidden_state,
|
||||
pooler_output=pooled_output,
|
||||
hidden_states=encoder_outputs.hidden_states,
|
||||
attentions=encoder_outputs.attentions,
|
||||
)
|
||||
323
modeling_internvl_chat.py
Normal file
323
modeling_internvl_chat.py
Normal file
@@ -0,0 +1,323 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2024 OpenGVLab
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# --------------------------------------------------------
|
||||
import warnings
|
||||
from typing import Any, List, Optional, Tuple, Union
|
||||
|
||||
import torch.utils.checkpoint
|
||||
from torch import nn
|
||||
from torch.nn import CrossEntropyLoss
|
||||
from transformers import (AutoModel, GenerationConfig, LlamaForCausalLM,
|
||||
LlamaTokenizer)
|
||||
from transformers.modeling_outputs import CausalLMOutputWithPast
|
||||
from transformers.modeling_utils import PreTrainedModel
|
||||
from transformers.utils import ModelOutput, logging
|
||||
|
||||
from .configuration_internvl_chat import InternVLChatConfig
|
||||
from .conversation import get_conv_template
|
||||
from .modeling_intern_vit import InternVisionModel
|
||||
from .modeling_phi3 import Phi3ForCausalLM
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
class InternVLChatModel(PreTrainedModel):
|
||||
config_class = InternVLChatConfig
|
||||
main_input_name = 'pixel_values'
|
||||
_no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'Phi3DecoderLayer']
|
||||
|
||||
def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
|
||||
super().__init__(config)
|
||||
|
||||
image_size = config.force_image_size or config.vision_config.image_size
|
||||
patch_size = config.vision_config.patch_size
|
||||
self.patch_size = patch_size
|
||||
self.select_layer = config.select_layer
|
||||
self.template = config.template
|
||||
self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
|
||||
self.downsample_ratio = config.downsample_ratio
|
||||
self.ps_version = config.ps_version
|
||||
|
||||
logger.info(f'num_image_token: {self.num_image_token}')
|
||||
logger.info(f'ps_version: {self.ps_version}')
|
||||
if vision_model is not None:
|
||||
self.vision_model = vision_model
|
||||
else:
|
||||
self.vision_model = InternVisionModel(config.vision_config)
|
||||
if language_model is not None:
|
||||
self.language_model = language_model
|
||||
else:
|
||||
if config.llm_config.architectures[0] == 'LlamaForCausalLM':
|
||||
self.language_model = LlamaForCausalLM(config.llm_config)
|
||||
elif config.llm_config.architectures[0] == 'Phi3ForCausalLM':
|
||||
self.language_model = Phi3ForCausalLM(config.llm_config)
|
||||
else:
|
||||
raise NotImplementedError(f'{config.llm_config.architectures[0]} is not implemented.')
|
||||
|
||||
vit_hidden_size = config.vision_config.hidden_size
|
||||
llm_hidden_size = config.llm_config.hidden_size
|
||||
|
||||
self.mlp1 = nn.Sequential(
|
||||
nn.LayerNorm(vit_hidden_size * int(1 / self.downsample_ratio) ** 2),
|
||||
nn.Linear(vit_hidden_size * int(1 / self.downsample_ratio) ** 2, llm_hidden_size),
|
||||
nn.GELU(),
|
||||
nn.Linear(llm_hidden_size, llm_hidden_size)
|
||||
)
|
||||
|
||||
self.img_context_token_id = None
|
||||
|
||||
def forward(
|
||||
self,
|
||||
pixel_values: torch.FloatTensor,
|
||||
input_ids: torch.LongTensor = None,
|
||||
attention_mask: Optional[torch.Tensor] = None,
|
||||
position_ids: Optional[torch.LongTensor] = None,
|
||||
image_flags: Optional[torch.LongTensor] = None,
|
||||
past_key_values: Optional[List[torch.FloatTensor]] = None,
|
||||
labels: Optional[torch.LongTensor] = None,
|
||||
use_cache: Optional[bool] = None,
|
||||
output_attentions: Optional[bool] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
) -> Union[Tuple, CausalLMOutputWithPast]:
|
||||
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
||||
|
||||
image_flags = image_flags.squeeze(-1)
|
||||
input_embeds = self.language_model.get_input_embeddings()(input_ids)
|
||||
|
||||
vit_embeds = self.extract_feature(pixel_values)
|
||||
vit_embeds = vit_embeds[image_flags == 1]
|
||||
vit_batch_size = pixel_values.shape[0]
|
||||
|
||||
B, N, C = input_embeds.shape
|
||||
input_embeds = input_embeds.reshape(B * N, C)
|
||||
|
||||
if torch.distributed.get_rank() == 0:
|
||||
print(f'dynamic ViT batch size: {vit_batch_size}, images per sample: {vit_batch_size / B}, dynamic token length: {N}')
|
||||
|
||||
input_ids = input_ids.reshape(B * N)
|
||||
selected = (input_ids == self.img_context_token_id)
|
||||
try:
|
||||
input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds.reshape(-1, C)
|
||||
except Exception as e:
|
||||
vit_embeds = vit_embeds.reshape(-1, C)
|
||||
print(f'warning: {e}, input_embeds[selected].shape={input_embeds[selected].shape}, '
|
||||
f'vit_embeds.shape={vit_embeds.shape}')
|
||||
n_token = selected.sum()
|
||||
input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds[:n_token]
|
||||
|
||||
input_embeds = input_embeds.reshape(B, N, C)
|
||||
|
||||
outputs = self.language_model(
|
||||
inputs_embeds=input_embeds,
|
||||
attention_mask=attention_mask,
|
||||
position_ids=position_ids,
|
||||
past_key_values=past_key_values,
|
||||
use_cache=use_cache,
|
||||
output_attentions=output_attentions,
|
||||
output_hidden_states=output_hidden_states,
|
||||
return_dict=return_dict,
|
||||
)
|
||||
logits = outputs.logits
|
||||
|
||||
loss = None
|
||||
if labels is not None:
|
||||
# Shift so that tokens < n predict n
|
||||
shift_logits = logits[..., :-1, :].contiguous()
|
||||
shift_labels = labels[..., 1:].contiguous()
|
||||
# Flatten the tokens
|
||||
loss_fct = CrossEntropyLoss()
|
||||
shift_logits = shift_logits.view(-1, self.language_model.config.vocab_size)
|
||||
shift_labels = shift_labels.view(-1)
|
||||
# Enable model parallelism
|
||||
shift_labels = shift_labels.to(shift_logits.device)
|
||||
loss = loss_fct(shift_logits, shift_labels)
|
||||
|
||||
if not return_dict:
|
||||
output = (logits,) + outputs[1:]
|
||||
return (loss,) + output if loss is not None else output
|
||||
|
||||
return CausalLMOutputWithPast(
|
||||
loss=loss,
|
||||
logits=logits,
|
||||
past_key_values=outputs.past_key_values,
|
||||
hidden_states=outputs.hidden_states,
|
||||
attentions=outputs.attentions,
|
||||
)
|
||||
|
||||
def pixel_shuffle(self, x, scale_factor=0.5):
|
||||
n, w, h, c = x.size()
|
||||
# N, W, H, C --> N, W, H * scale, C // scale
|
||||
x = x.view(n, w, int(h * scale_factor), int(c / scale_factor))
|
||||
# N, W, H * scale, C // scale --> N, H * scale, W, C // scale
|
||||
x = x.permute(0, 2, 1, 3).contiguous()
|
||||
# N, H * scale, W, C // scale --> N, H * scale, W * scale, C // (scale ** 2)
|
||||
x = x.view(n, int(h * scale_factor), int(w * scale_factor),
|
||||
int(c / (scale_factor * scale_factor)))
|
||||
if self.ps_version == 'v1':
|
||||
warnings.warn("In ps_version 'v1', the height and width have not been swapped back, "
|
||||
'which results in a transposed image.')
|
||||
else:
|
||||
x = x.permute(0, 2, 1, 3).contiguous()
|
||||
return x
|
||||
|
||||
def extract_feature(self, pixel_values):
|
||||
if self.select_layer == -1:
|
||||
vit_embeds = self.vision_model(
|
||||
pixel_values=pixel_values,
|
||||
output_hidden_states=False,
|
||||
return_dict=True).last_hidden_state
|
||||
else:
|
||||
vit_embeds = self.vision_model(
|
||||
pixel_values=pixel_values,
|
||||
output_hidden_states=True,
|
||||
return_dict=True).hidden_states[self.select_layer]
|
||||
vit_embeds = vit_embeds[:, 1:, :]
|
||||
|
||||
h = w = int(vit_embeds.shape[1] ** 0.5)
|
||||
vit_embeds = vit_embeds.reshape(vit_embeds.shape[0], h, w, -1)
|
||||
vit_embeds = self.pixel_shuffle(vit_embeds, scale_factor=self.downsample_ratio)
|
||||
vit_embeds = vit_embeds.reshape(vit_embeds.shape[0], -1, vit_embeds.shape[-1])
|
||||
vit_embeds = self.mlp1(vit_embeds)
|
||||
return vit_embeds
|
||||
|
||||
def batch_chat(self, tokenizer, pixel_values, num_patches_list, questions, generation_config, history=None,
|
||||
return_history=False, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>',
|
||||
IMG_CONTEXT_TOKEN='<IMG_CONTEXT>', verbose=False):
|
||||
if history is not None or return_history:
|
||||
print('Now multi-turn chat is not supported in batch_chat.')
|
||||
raise NotImplementedError
|
||||
img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
|
||||
self.img_context_token_id = img_context_token_id
|
||||
|
||||
from .conversation import get_conv_template
|
||||
|
||||
queries = []
|
||||
if verbose:
|
||||
image_bs = pixel_values.shape[0]
|
||||
print(f'dynamic ViT batch size: {image_bs}, num_patches_list: {num_patches_list}')
|
||||
for idx, num_patches in enumerate(num_patches_list):
|
||||
image_token = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
|
||||
question = image_token + '\n' + questions[idx]
|
||||
template = get_conv_template(self.template)
|
||||
template.append_message(template.roles[0], question)
|
||||
template.append_message(template.roles[1], None)
|
||||
query = template.get_prompt()
|
||||
queries.append(query)
|
||||
tokenizer.padding_side = 'left'
|
||||
model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
|
||||
input_ids = model_inputs['input_ids'].cuda()
|
||||
attention_mask = model_inputs['attention_mask'].cuda()
|
||||
eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
|
||||
generation_config['eos_token_id'] = eos_token_id
|
||||
|
||||
generation_output = self.generate(
|
||||
pixel_values=pixel_values,
|
||||
input_ids=input_ids,
|
||||
attention_mask=attention_mask,
|
||||
**generation_config
|
||||
)
|
||||
responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
|
||||
responses = [response.split(template.sep)[0].strip() for response in responses]
|
||||
return responses
|
||||
|
||||
def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
|
||||
num_patches_list=None, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>',
|
||||
verbose=False):
|
||||
|
||||
if history is None and pixel_values is not None and '<image>' not in question:
|
||||
question = '<image>\n' + question
|
||||
|
||||
if num_patches_list is None:
|
||||
num_patches_list = [pixel_values.shape[0]] if pixel_values is not None else []
|
||||
assert pixel_values is None or len(pixel_values) == sum(num_patches_list)
|
||||
|
||||
img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
|
||||
self.img_context_token_id = img_context_token_id
|
||||
|
||||
template = get_conv_template(self.template)
|
||||
eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
|
||||
|
||||
history = [] if history is None else history
|
||||
for (old_question, old_answer) in history:
|
||||
template.append_message(template.roles[0], old_question)
|
||||
template.append_message(template.roles[1], old_answer)
|
||||
template.append_message(template.roles[0], question)
|
||||
template.append_message(template.roles[1], None)
|
||||
query = template.get_prompt()
|
||||
|
||||
if verbose and pixel_values is not None:
|
||||
image_bs = pixel_values.shape[0]
|
||||
print(f'dynamic ViT batch size: {image_bs}')
|
||||
|
||||
for num_patches in num_patches_list:
|
||||
image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
|
||||
query = query.replace('<image>', image_tokens, 1)
|
||||
|
||||
model_inputs = tokenizer(query, return_tensors='pt')
|
||||
input_ids = model_inputs['input_ids'].cuda()
|
||||
attention_mask = model_inputs['attention_mask'].cuda()
|
||||
generation_config['eos_token_id'] = eos_token_id
|
||||
generation_output = self.generate(
|
||||
pixel_values=pixel_values,
|
||||
input_ids=input_ids,
|
||||
attention_mask=attention_mask,
|
||||
**generation_config
|
||||
)
|
||||
response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
|
||||
response = response.split(template.sep)[0].strip()
|
||||
history.append((question, response))
|
||||
if return_history:
|
||||
return response, history
|
||||
else:
|
||||
query_to_print = query.replace(IMG_CONTEXT_TOKEN, '')
|
||||
query_to_print = query_to_print.replace(f'{IMG_START_TOKEN}{IMG_END_TOKEN}', '<image>')
|
||||
if verbose:
|
||||
print(query_to_print, response)
|
||||
return response
|
||||
|
||||
@torch.no_grad()
|
||||
def generate(
|
||||
self,
|
||||
pixel_values: Optional[torch.FloatTensor] = None,
|
||||
input_ids: Optional[torch.FloatTensor] = None,
|
||||
attention_mask: Optional[torch.LongTensor] = None,
|
||||
visual_features: Optional[torch.FloatTensor] = None,
|
||||
generation_config: Optional[GenerationConfig] = None,
|
||||
output_hidden_states: Optional[bool] = None,
|
||||
return_dict: Optional[bool] = None,
|
||||
**generate_kwargs,
|
||||
) -> torch.LongTensor:
|
||||
|
||||
assert self.img_context_token_id is not None
|
||||
if pixel_values is not None:
|
||||
if visual_features is not None:
|
||||
vit_embeds = visual_features
|
||||
else:
|
||||
vit_embeds = self.extract_feature(pixel_values)
|
||||
input_embeds = self.language_model.get_input_embeddings()(input_ids)
|
||||
B, N, C = input_embeds.shape
|
||||
input_embeds = input_embeds.reshape(B * N, C)
|
||||
|
||||
input_ids = input_ids.reshape(B * N)
|
||||
selected = (input_ids == self.img_context_token_id)
|
||||
assert selected.sum() != 0
|
||||
input_embeds[selected] = vit_embeds.reshape(-1, C).to(input_embeds.device)
|
||||
|
||||
input_embeds = input_embeds.reshape(B, N, C)
|
||||
else:
|
||||
input_embeds = self.language_model.get_input_embeddings()(input_ids)
|
||||
|
||||
outputs = self.language_model.generate(
|
||||
inputs_embeds=input_embeds,
|
||||
attention_mask=attention_mask,
|
||||
generation_config=generation_config,
|
||||
output_hidden_states=output_hidden_states,
|
||||
return_dict=return_dict,
|
||||
use_cache=True,
|
||||
**generate_kwargs,
|
||||
)
|
||||
|
||||
return outputs
|
||||
1601
modeling_phi3.py
Normal file
1601
modeling_phi3.py
Normal file
File diff suppressed because it is too large
Load Diff
55
special_tokens_map.json
Normal file
55
special_tokens_map.json
Normal file
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<img>",
|
||||
"</img>",
|
||||
"<IMG_CONTEXT>",
|
||||
"<quad>",
|
||||
"</quad>",
|
||||
"<ref>",
|
||||
"</ref>",
|
||||
"<box>",
|
||||
"</box>",
|
||||
{
|
||||
"content": "<point>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
{
|
||||
"content": "</point>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
233
tokenizer_config.json
Normal file
233
tokenizer_config.json
Normal file
@@ -0,0 +1,233 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": true,
|
||||
"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": true
|
||||
},
|
||||
"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": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32007": {
|
||||
"content": "<|end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"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": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32011": {
|
||||
"content": "<img>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32012": {
|
||||
"content": "</img>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32013": {
|
||||
"content": "<IMG_CONTEXT>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32014": {
|
||||
"content": "<quad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32015": {
|
||||
"content": "</quad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32016": {
|
||||
"content": "<ref>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32017": {
|
||||
"content": "</ref>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32018": {
|
||||
"content": "<box>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32019": {
|
||||
"content": "</box>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32020": {
|
||||
"content": "<point>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32021": {
|
||||
"content": "</point>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<img>",
|
||||
"</img>",
|
||||
"<IMG_CONTEXT>",
|
||||
"<quad>",
|
||||
"</quad>",
|
||||
"<ref>",
|
||||
"</ref>",
|
||||
"<box>",
|
||||
"</box>",
|
||||
"<point>",
|
||||
"</point>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": false,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user