初始化项目，由ModelHub XC社区提供模型
Model: AI4Chem/ChemVLM-8B Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
162
README.md
Normal file
162
README.md
Normal file
@@ -0,0 +1,162 @@
|
||||
---
|
||||
pipeline_tag: image-text-to-text
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# ChemVLM-8B: A Multimodal Large Language Model for Chemistry
|
||||
|
||||
This is the 8b version of ChemVLM, a multimodal large language model designed for chemical applications.
|
||||
|
||||
## Paper
|
||||
|
||||
[ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area](https://huggingface.co/papers/2408.07246)
|
||||
|
||||
### Abstract
|
||||
|
||||
Large Language Models (LLMs) have achieved remarkable success and have been applied across various scientific fields, including chemistry. However, many chemical tasks require the processing of visual information, which cannot be successfully handled by existing chemical LLMs. This brings a growing need for models capable of integrating multimodal information in the chemical domain. In this paper, we introduce **ChemVLM**, an open-source chemical multimodal large language model specifically designed for chemical applications. ChemVLM is trained on a carefully curated bilingual multimodal dataset that enhances its ability to understand both textual and visual chemical information, including molecular structures, reactions, and chemistry examination questions. We develop three datasets for comprehensive evaluation, tailored to Chemical Optical Character Recognition (OCR), Multimodal Chemical Reasoning (MMCR), and Multimodal Molecule Understanding tasks. We benchmark ChemVLM against a range of open-source and proprietary multimodal large language models on various tasks. Experimental results demonstrate that ChemVLM achieves competitive performance across all evaluated tasks. Our model can be found at https://huggingface.co/AI4Chem/ChemVLM-26B.
|
||||
|
||||
## Model Description
|
||||
|
||||
The architecture of ChemVLM is based on InternVLM and incorporates both vision and language processing components. The model is trained on a bilingual multimodal dataset containing chemical information, including molecular structures, reactions, and chemistry exam questions. More details about the architecture can be found in the [Github README](https://github.com/AI4Chem/ChemVlm).
|
||||
|
||||
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@inproceedings{li2025chemvlm,
|
||||
title={Chemvlm: Exploring the power of multimodal large language models in chemistry area},
|
||||
author={Li, Junxian and Zhang, Di and Wang, Xunzhi and Hao, Zeying and Lei, Jingdi and Tan, Qian and Zhou, Cai and Liu, Wei and Yang, Yaotian and Xiong, Xinrui and others},
|
||||
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
|
||||
volume={39},
|
||||
number={1},
|
||||
pages={415--423},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
|
||||
## Codebase and Datasets
|
||||
|
||||
Codebase and datasets can be found at https://github.com/AI4Chem/ChemVlm.
|
||||
Some training data can be found at https://huggingface.co/datasets/di-zhang-fdu/chemvlm-sft-datasets.
|
||||
|
||||
## Performances of our 8b model on several tasks
|
||||
|
||||
| Datasets | MMChemOCR | CMMU | MMCR-bench | Reaction type |
|
||||
| :----- | :----- | :----- |:----- |:----- |
|
||||
|metrics| tanimoto similarity\tani@1.0 | score(\%, GPT-4o helps judge) | score(\%, GPT-4o helps judge) | Accuracy(\%) |
|
||||
|scores of ChemVLM-8b| 81.75/57.69 | 52.7(SOTA) | 33.6 | 16.79 |
|
||||
|
||||
|
||||
## Quick Start
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelforCasualLM
|
||||
import torch
|
||||
import torchvision.transforms as T
|
||||
import transformers
|
||||
from torchvision.transforms.functional import InterpolationMode
|
||||
|
||||
|
||||
IMAGENET_MEAN = (0.485, 0.456, 0.406)
|
||||
IMAGENET_STD = (0.229, 0.224, 0.225)
|
||||
|
||||
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=6, 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=6):
|
||||
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
|
||||
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained('AI4Chem/ChemVLM-8B', trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"AI4Chem/ChemVLM-8B",
|
||||
torch_dtype=torch.bfloat16,
|
||||
low_cpu_mem_usage=True,
|
||||
trust_remote_code=True
|
||||
).cuda().eval()
|
||||
|
||||
query = "Please describe the molecule in the image."
|
||||
image_path = "your image path"
|
||||
pixel_values = load_image(image_path, max_num=6).to(torch.bfloat16).cuda()
|
||||
|
||||
gen_kwargs = {"max_length": 1000, "do_sample": True, "temperature": 0.7, "top_p": 0.9}
|
||||
|
||||
response = model.chat(tokenizer, pixel_values, query, gen_kwargs)
|
||||
print(response)
|
||||
```
|
||||
Install required libraries with `pip install transformers>=4.37.0 sentencepiece einops timm accelerate>=0.26.0`. Make sure to have `torch` and `torchvision` installed as well.
|
||||
11
added_tokens.json
Normal file
11
added_tokens.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"</box>": 92552,
|
||||
"</img>": 92545,
|
||||
"</quad>": 92548,
|
||||
"</ref>": 92550,
|
||||
"<IMG_CONTEXT>": 92546,
|
||||
"<box>": 92551,
|
||||
"<img>": 92544,
|
||||
"<quad>": 92547,
|
||||
"<ref>": 92549
|
||||
}
|
||||
201
config.json
Normal file
201
config.json
Normal file
@@ -0,0 +1,201 @@
|
||||
{
|
||||
"_commit_hash": null,
|
||||
"_name_or_path": "AI4Chem/ChemVLM-8B",
|
||||
"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": "internlm/internlm2_5-7b-chat",
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"InternLM2ForCausalLM"
|
||||
],
|
||||
"attn_implementation": "flash_attention_2",
|
||||
"auto_map": {
|
||||
"AutoConfig": "configuration_internlm2.InternLM2Config",
|
||||
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
|
||||
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
|
||||
},
|
||||
"bad_words_ids": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"bias": false,
|
||||
"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,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"eos_token_id": 2,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"finetuning_task": null,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"is_decoder": false,
|
||||
"is_encoder_decoder": false,
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"length_penalty": 1.0,
|
||||
"max_length": 20,
|
||||
"max_position_embeddings": 32768,
|
||||
"min_length": 0,
|
||||
"model_type": "internlm2",
|
||||
"no_repeat_ngram_size": 0,
|
||||
"num_attention_heads": 32,
|
||||
"num_beam_groups": 1,
|
||||
"num_beams": 1,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"num_return_sequences": 1,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"output_scores": false,
|
||||
"pad_token_id": 2,
|
||||
"prefix": null,
|
||||
"pretraining_tp": 1,
|
||||
"problem_type": null,
|
||||
"pruned_heads": {},
|
||||
"remove_invalid_values": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"return_dict": true,
|
||||
"return_dict_in_generate": false,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 2.0,
|
||||
"type": "dynamic"
|
||||
},
|
||||
"rope_theta": 1000000,
|
||||
"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": false,
|
||||
"tokenizer_class": null,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"torchscript": false,
|
||||
"transformers_version": "4.37.2",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": true,
|
||||
"use_cache": false,
|
||||
"vocab_size": 92553
|
||||
},
|
||||
"max_dynamic_patch": 12,
|
||||
"min_dynamic_patch": 1,
|
||||
"model_type": "internvl_chat",
|
||||
"pad2square": false,
|
||||
"ps_version": "v2",
|
||||
"select_layer": -1,
|
||||
"template": "internlm2-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": 0.0,
|
||||
"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": 1.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"torchscript": false,
|
||||
"transformers_version": "4.37.2",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": true,
|
||||
"use_flash_attn": true
|
||||
}
|
||||
}
|
||||
120
configuration_intern_vit.py
Normal file
120
configuration_intern_vit.py
Normal file
@@ -0,0 +1,120 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2024 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)
|
||||
150
configuration_internlm2.py
Normal file
150
configuration_internlm2.py
Normal file
@@ -0,0 +1,150 @@
|
||||
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# This code is based on transformers/src/transformers/models/llama/configuration_llama.py
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
""" InternLM2 model configuration"""
|
||||
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
from transformers.utils import logging
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
INTERNLM2_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
|
||||
|
||||
|
||||
# Modified from transformers.model.llama.configuration_llama.LlamaConfig
|
||||
class InternLM2Config(PretrainedConfig):
|
||||
r"""
|
||||
This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate
|
||||
an InternLM2 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 InternLM2-7B.
|
||||
|
||||
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 32000):
|
||||
Vocabulary size of the InternLM2 model. Defines the number of different tokens that can be represented by the
|
||||
`inputs_ids` passed when calling [`InternLM2Model`]
|
||||
hidden_size (`int`, *optional*, defaults to 4096):
|
||||
Dimension of the hidden representations.
|
||||
intermediate_size (`int`, *optional*, defaults to 11008):
|
||||
Dimension of the MLP representations.
|
||||
num_hidden_layers (`int`, *optional*, defaults to 32):
|
||||
Number of hidden layers in the Transformer encoder.
|
||||
num_attention_heads (`int`, *optional*, defaults to 32):
|
||||
Number of attention heads for each attention layer in the Transformer encoder.
|
||||
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`.
|
||||
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 2048):
|
||||
The maximum sequence length that this model might ever be used with. Typically set this to something large
|
||||
just in case (e.g., 512 or 1024 or 2048).
|
||||
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-12):
|
||||
The epsilon used by the rms normalization layers.
|
||||
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`.
|
||||
tie_word_embeddings(`bool`, *optional*, defaults to `False`):
|
||||
Whether to tie weight embeddings
|
||||
Example:
|
||||
|
||||
"""
|
||||
model_type = 'internlm2'
|
||||
_auto_class = 'AutoConfig'
|
||||
|
||||
def __init__( # pylint: disable=W0102
|
||||
self,
|
||||
vocab_size=103168,
|
||||
hidden_size=4096,
|
||||
intermediate_size=11008,
|
||||
num_hidden_layers=32,
|
||||
num_attention_heads=32,
|
||||
num_key_value_heads=None,
|
||||
hidden_act='silu',
|
||||
max_position_embeddings=2048,
|
||||
initializer_range=0.02,
|
||||
rms_norm_eps=1e-6,
|
||||
use_cache=True,
|
||||
pad_token_id=0,
|
||||
bos_token_id=1,
|
||||
eos_token_id=2,
|
||||
tie_word_embeddings=False,
|
||||
bias=True,
|
||||
rope_theta=10000,
|
||||
rope_scaling=None,
|
||||
attn_implementation='eager',
|
||||
**kwargs,
|
||||
):
|
||||
self.vocab_size = vocab_size
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.hidden_size = hidden_size
|
||||
self.intermediate_size = intermediate_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.bias = bias
|
||||
|
||||
if num_key_value_heads is None:
|
||||
num_key_value_heads = num_attention_heads
|
||||
self.num_key_value_heads = num_key_value_heads
|
||||
|
||||
self.hidden_act = hidden_act
|
||||
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.attn_implementation = attn_implementation
|
||||
if self.attn_implementation is None:
|
||||
self.attn_implementation = 'eager'
|
||||
super().__init__(
|
||||
pad_token_id=pad_token_id,
|
||||
bos_token_id=bos_token_id,
|
||||
eos_token_id=eos_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) != 2:
|
||||
raise ValueError(
|
||||
'`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, '
|
||||
f'got {self.rope_scaling}'
|
||||
)
|
||||
rope_scaling_type = self.rope_scaling.get('type', None)
|
||||
rope_scaling_factor = self.rope_scaling.get('factor', None)
|
||||
if rope_scaling_type is None or rope_scaling_type not in ['linear', 'dynamic']:
|
||||
raise ValueError(
|
||||
f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
|
||||
)
|
||||
if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor < 1.0:
|
||||
raise ValueError(f"`rope_scaling`'s factor field must be a float >= 1, got {rope_scaling_factor}")
|
||||
96
configuration_internvl_chat.py
Normal file
96
configuration_internvl_chat.py
Normal file
@@ -0,0 +1,96 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2024 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_internlm2 import InternLM2Config
|
||||
|
||||
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,
|
||||
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 = {'architectures': ['InternVisionModel']}
|
||||
logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
|
||||
|
||||
if llm_config is None:
|
||||
llm_config = {'architectures': ['InternLM2ForCausalLM']}
|
||||
logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
|
||||
|
||||
self.vision_config = InternVisionConfig(**vision_config)
|
||||
if llm_config.get('architectures')[0] == 'LlamaForCausalLM':
|
||||
self.llm_config = LlamaConfig(**llm_config)
|
||||
elif llm_config.get('architectures')[0] == 'InternLM2ForCausalLM':
|
||||
self.llm_config = InternLM2Config(**llm_config)
|
||||
else:
|
||||
raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0]))
|
||||
self.use_backbone_lora = use_backbone_lora
|
||||
self.use_llm_lora = use_llm_lora
|
||||
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['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
|
||||
391
conversation.py
Normal file
391
conversation.py
Normal file
@@ -0,0 +1,391 @@
|
||||
"""
|
||||
Conversation prompt templates.
|
||||
|
||||
We kindly request that you import fastchat instead of copying this file if you wish to use it.
|
||||
If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
|
||||
|
||||
Modified from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
|
||||
"""
|
||||
|
||||
import dataclasses
|
||||
from enum import IntEnum, auto
|
||||
from typing import 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()
|
||||
|
||||
|
||||
# Both Hermes-2 and internlm2-chat are chatml-format conversation templates. The difference
|
||||
# is that during training, the preprocessing function for the Hermes-2 template doesn't add
|
||||
# <s> at the beginning of the tokenized sequence, while the internlm2-chat template does.
|
||||
# Therefore, they are completely equivalent during inference.
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='Hermes-2',
|
||||
system_template='<|im_start|>system\n{system_message}',
|
||||
# note: The new system prompt was not used here to avoid changes in benchmark performance.
|
||||
# system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
|
||||
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_str='<|endoftext|>',
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='internlm2-chat',
|
||||
system_template='<|im_start|>system\n{system_message}',
|
||||
# note: The new system prompt was not used here to avoid changes in benchmark performance.
|
||||
# system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
|
||||
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|>',
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='phi3-chat',
|
||||
system_template='<|system|>\n{system_message}',
|
||||
# note: The new system prompt was not used here to avoid changes in benchmark performance.
|
||||
# system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
|
||||
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|>',
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name='internvl2_5',
|
||||
system_template='<|im_start|>system\n{system_message}',
|
||||
system_message='你是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
|
||||
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
|
||||
sep_style=SeparatorStyle.MPT,
|
||||
sep='<|im_end|>\n',
|
||||
)
|
||||
)
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": [
|
||||
92542,
|
||||
92543
|
||||
],
|
||||
"transformers_version": "4.37.2"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6dd7ac88d953c04f29e214095cb4e04b39a4fa010736add760df0c1e41fc22b
|
||||
size 4939944336
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8fff6c3ffca85d376d44e5ab2bf1093b5f4004f7520b14441b6582ea34df5e1
|
||||
size 4915914584
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98f0a947e3e7a24a363905d4e29c29d0859ad596a84e3a4982b9bc00e40fbf60
|
||||
size 4915914592
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3da827dabeb853079037c1063c9a4a7f8957c450443bbb3c20871658bf91db85
|
||||
size 1379026920
|
||||
580
model.safetensors.index.json
Normal file
580
model.safetensors.index.json
Normal file
@@ -0,0 +1,580 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16150730752
|
||||
},
|
||||
"weight_map": {
|
||||
"language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.output.weight": "model-00004-of-00004.safetensors",
|
||||
"mlp1.0.bias": "model-00004-of-00004.safetensors",
|
||||
"mlp1.0.weight": "model-00004-of-00004.safetensors",
|
||||
"mlp1.1.bias": "model-00004-of-00004.safetensors",
|
||||
"mlp1.1.weight": "model-00004-of-00004.safetensors",
|
||||
"mlp1.3.bias": "model-00004-of-00004.safetensors",
|
||||
"mlp1.3.weight": "model-00004-of-00004.safetensors",
|
||||
"vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
|
||||
"vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
430
modeling_intern_vit.py
Normal file
430
modeling_intern_vit.py
Normal file
@@ -0,0 +1,430 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2024 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:
|
||||
from flash_attn.bert_padding import pad_input, unpad_input
|
||||
from flash_attn.flash_attn_interface import \
|
||||
flash_attn_varlen_qkvpacked_func
|
||||
has_flash_attn = True
|
||||
except:
|
||||
print('FlashAttention2 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_varlen_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_varlen_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_varlen_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).to(hidden_states.dtype)) * self.ls1)
|
||||
|
||||
hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states).to(hidden_states.dtype)) * 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'
|
||||
_supports_flash_attn_2 = True
|
||||
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,
|
||||
)
|
||||
1415
modeling_internlm2.py
Normal file
1415
modeling_internlm2.py
Normal file
File diff suppressed because it is too large
Load Diff
349
modeling_internvl_chat.py
Normal file
349
modeling_internvl_chat.py
Normal file
@@ -0,0 +1,349 @@
|
||||
# --------------------------------------------------------
|
||||
# InternVL
|
||||
# Copyright (c) 2024 OpenGVLab
|
||||
# Licensed under The MIT License [see LICENSE for details]
|
||||
# --------------------------------------------------------
|
||||
|
||||
import warnings
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
import torch.utils.checkpoint
|
||||
import transformers
|
||||
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, has_flash_attn
|
||||
from .modeling_internlm2 import InternLM2ForCausalLM
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
|
||||
def version_cmp(v1, v2, op='eq'):
|
||||
import operator
|
||||
|
||||
from packaging import version
|
||||
op_func = getattr(operator, op)
|
||||
return op_func(version.parse(v1), version.parse(v2))
|
||||
|
||||
|
||||
class InternVLChatModel(PreTrainedModel):
|
||||
config_class = InternVLChatConfig
|
||||
main_input_name = 'pixel_values'
|
||||
base_model_prefix = 'language_model'
|
||||
_supports_flash_attn_2 = True
|
||||
_no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
|
||||
|
||||
def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
|
||||
super().__init__(config)
|
||||
|
||||
assert version_cmp(transformers.__version__, '4.37.0', 'ge')
|
||||
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
|
||||
use_flash_attn = use_flash_attn if has_flash_attn else False
|
||||
config.vision_config.use_flash_attn = True if use_flash_attn else False
|
||||
config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'
|
||||
|
||||
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] == 'InternLM2ForCausalLM':
|
||||
self.language_model = InternLM2ForCausalLM(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
|
||||
self.conv_template = get_conv_template(self.template)
|
||||
self.system_message = self.conv_template.system_message
|
||||
|
||||
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).clone()
|
||||
|
||||
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.is_initialized() and 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, questions, generation_config, num_patches_list=None,
|
||||
history=None, return_history=False, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>',
|
||||
IMG_CONTEXT_TOKEN='<IMG_CONTEXT>', verbose=False, image_counts=None):
|
||||
if history is not None or return_history:
|
||||
print('Now multi-turn chat is not supported in batch_chat.')
|
||||
raise NotImplementedError
|
||||
|
||||
if image_counts is not None:
|
||||
num_patches_list = image_counts
|
||||
print('Warning: `image_counts` is deprecated. Please use `num_patches_list` instead.')
|
||||
|
||||
img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
|
||||
self.img_context_token_id = img_context_token_id
|
||||
|
||||
if verbose and pixel_values is not None:
|
||||
image_bs = pixel_values.shape[0]
|
||||
print(f'dynamic ViT batch size: {image_bs}')
|
||||
|
||||
queries = []
|
||||
for idx, num_patches in enumerate(num_patches_list):
|
||||
question = questions[idx]
|
||||
if pixel_values is not None and '<image>' not in question:
|
||||
question = '<image>\n' + question
|
||||
template = get_conv_template(self.template)
|
||||
template.system_message = self.system_message
|
||||
template.append_message(template.roles[0], question)
|
||||
template.append_message(template.roles[1], None)
|
||||
query = template.get_prompt()
|
||||
|
||||
image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
|
||||
query = query.replace('<image>', image_tokens, 1)
|
||||
queries.append(query)
|
||||
|
||||
tokenizer.padding_side = 'left'
|
||||
model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
|
||||
input_ids = model_inputs['input_ids'].to(self.device)
|
||||
attention_mask = model_inputs['attention_mask'].to(self.device)
|
||||
eos_token_id = tokenizer.convert_tokens_to_ids(template.sep.strip())
|
||||
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.strip())[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)
|
||||
template.system_message = self.system_message
|
||||
eos_token_id = tokenizer.convert_tokens_to_ids(template.sep.strip())
|
||||
|
||||
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'].to(self.device)
|
||||
attention_mask = model_inputs['attention_mask'].to(self.device)
|
||||
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.strip())[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,
|
||||
**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,
|
||||
use_cache=True,
|
||||
**generate_kwargs,
|
||||
)
|
||||
|
||||
return outputs
|
||||
19
preprocessor_config.json
Normal file
19
preprocessor_config.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"crop_size": 448,
|
||||
"do_center_crop": true,
|
||||
"do_normalize": true,
|
||||
"do_resize": true,
|
||||
"feature_extractor_type": "CLIPFeatureExtractor",
|
||||
"image_mean": [
|
||||
0.485,
|
||||
0.456,
|
||||
0.406
|
||||
],
|
||||
"image_std": [
|
||||
0.229,
|
||||
0.224,
|
||||
0.225
|
||||
],
|
||||
"resample": 3,
|
||||
"size": 448
|
||||
}
|
||||
47
special_tokens_map.json
Normal file
47
special_tokens_map.json
Normal file
@@ -0,0 +1,47 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|action_start|>",
|
||||
"<|action_end|>",
|
||||
"<|interpreter|>",
|
||||
"<|plugin|>",
|
||||
"<img>",
|
||||
"</img>",
|
||||
"<IMG_CONTEXT>",
|
||||
"<quad>",
|
||||
"</quad>",
|
||||
"<ref>",
|
||||
"</ref>",
|
||||
"<box>",
|
||||
"</box>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
235
tokenization_internlm2.py
Normal file
235
tokenization_internlm2.py
Normal file
@@ -0,0 +1,235 @@
|
||||
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
|
||||
#
|
||||
# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
"""Tokenization classes for InternLM."""
|
||||
import os
|
||||
from shutil import copyfile
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
import sentencepiece as spm
|
||||
from transformers.tokenization_utils import PreTrainedTokenizer
|
||||
from transformers.utils import logging
|
||||
|
||||
logger = logging.get_logger(__name__)
|
||||
|
||||
VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
|
||||
|
||||
PRETRAINED_VOCAB_FILES_MAP = {}
|
||||
|
||||
|
||||
# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
|
||||
class InternLM2Tokenizer(PreTrainedTokenizer):
|
||||
"""
|
||||
Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
|
||||
|
||||
Args:
|
||||
vocab_file (`str`):
|
||||
Path to the vocabulary file.
|
||||
"""
|
||||
|
||||
vocab_files_names = VOCAB_FILES_NAMES
|
||||
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
||||
model_input_names = ['input_ids', 'attention_mask']
|
||||
_auto_class = 'AutoTokenizer'
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vocab_file,
|
||||
unk_token='<unk>',
|
||||
bos_token='<s>',
|
||||
eos_token='</s>',
|
||||
pad_token='</s>',
|
||||
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
||||
add_bos_token=True,
|
||||
add_eos_token=False,
|
||||
decode_with_prefix_space=False,
|
||||
clean_up_tokenization_spaces=False,
|
||||
**kwargs,
|
||||
):
|
||||
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
||||
self.vocab_file = vocab_file
|
||||
self.add_bos_token = add_bos_token
|
||||
self.add_eos_token = add_eos_token
|
||||
self.decode_with_prefix_space = decode_with_prefix_space
|
||||
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
||||
self.sp_model.Load(vocab_file)
|
||||
self._no_prefix_space_tokens = None
|
||||
super().__init__(
|
||||
bos_token=bos_token,
|
||||
eos_token=eos_token,
|
||||
unk_token=unk_token,
|
||||
pad_token=pad_token,
|
||||
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
@property
|
||||
def no_prefix_space_tokens(self):
|
||||
if self._no_prefix_space_tokens is None:
|
||||
vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
|
||||
self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
|
||||
return self._no_prefix_space_tokens
|
||||
|
||||
@property
|
||||
def vocab_size(self):
|
||||
"""Returns vocab size"""
|
||||
return self.sp_model.get_piece_size()
|
||||
|
||||
@property
|
||||
def bos_token_id(self) -> Optional[int]:
|
||||
return self.sp_model.bos_id()
|
||||
|
||||
@property
|
||||
def eos_token_id(self) -> Optional[int]:
|
||||
return self.sp_model.eos_id()
|
||||
|
||||
def get_vocab(self):
|
||||
"""Returns vocab as a dict"""
|
||||
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
||||
vocab.update(self.added_tokens_encoder)
|
||||
return vocab
|
||||
|
||||
def _tokenize(self, text):
|
||||
"""Returns a tokenized string."""
|
||||
return self.sp_model.encode(text, out_type=str)
|
||||
|
||||
def _convert_token_to_id(self, token):
|
||||
"""Converts a token (str) in an id using the vocab."""
|
||||
return self.sp_model.piece_to_id(token)
|
||||
|
||||
def _convert_id_to_token(self, index):
|
||||
"""Converts an index (integer) in a token (str) using the vocab."""
|
||||
token = self.sp_model.IdToPiece(index)
|
||||
return token
|
||||
|
||||
def _maybe_add_prefix_space(self, tokens, decoded):
|
||||
if tokens and tokens[0] not in self.no_prefix_space_tokens:
|
||||
return ' ' + decoded
|
||||
else:
|
||||
return decoded
|
||||
|
||||
def convert_tokens_to_string(self, tokens):
|
||||
"""Converts a sequence of tokens (string) in a single string."""
|
||||
current_sub_tokens = []
|
||||
out_string = ''
|
||||
prev_is_special = False
|
||||
for token in tokens:
|
||||
# make sure that special tokens are not decoded using sentencepiece model
|
||||
if token in self.all_special_tokens:
|
||||
if not prev_is_special:
|
||||
out_string += ' '
|
||||
out_string += self.sp_model.decode(current_sub_tokens) + token
|
||||
prev_is_special = True
|
||||
current_sub_tokens = []
|
||||
else:
|
||||
current_sub_tokens.append(token)
|
||||
prev_is_special = False
|
||||
out_string += self.sp_model.decode(current_sub_tokens)
|
||||
out_string = self.clean_up_tokenization(out_string)
|
||||
out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
|
||||
return out_string[1:]
|
||||
|
||||
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
||||
"""
|
||||
Save the vocabulary and special tokens file to a directory.
|
||||
|
||||
Args:
|
||||
save_directory (`str`):
|
||||
The directory in which to save the vocabulary.
|
||||
|
||||
Returns:
|
||||
`Tuple(str)`: Paths to the files saved.
|
||||
"""
|
||||
if not os.path.isdir(save_directory):
|
||||
logger.error(f'Vocabulary path ({save_directory}) should be a directory')
|
||||
return
|
||||
out_vocab_file = os.path.join(
|
||||
save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
|
||||
)
|
||||
|
||||
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
||||
copyfile(self.vocab_file, out_vocab_file)
|
||||
elif not os.path.isfile(self.vocab_file):
|
||||
with open(out_vocab_file, 'wb') as fi:
|
||||
content_spiece_model = self.sp_model.serialized_model_proto()
|
||||
fi.write(content_spiece_model)
|
||||
|
||||
return (out_vocab_file,)
|
||||
|
||||
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
||||
if self.add_bos_token:
|
||||
bos_token_ids = [self.bos_token_id]
|
||||
else:
|
||||
bos_token_ids = []
|
||||
|
||||
output = bos_token_ids + token_ids_0
|
||||
|
||||
if token_ids_1 is not None:
|
||||
output = output + token_ids_1
|
||||
|
||||
if self.add_eos_token:
|
||||
output = output + [self.eos_token_id]
|
||||
|
||||
return output
|
||||
|
||||
def get_special_tokens_mask(
|
||||
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
||||
) -> List[int]:
|
||||
"""
|
||||
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
||||
special tokens using the tokenizer `prepare_for_model` method.
|
||||
|
||||
Args:
|
||||
token_ids_0 (`List[int]`):
|
||||
List of IDs.
|
||||
token_ids_1 (`List[int]`, *optional*):
|
||||
Optional second list of IDs for sequence pairs.
|
||||
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
||||
Whether or not the token list is already formatted with special tokens for the model.
|
||||
|
||||
Returns:
|
||||
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
||||
"""
|
||||
if already_has_special_tokens:
|
||||
return super().get_special_tokens_mask(
|
||||
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
|
||||
)
|
||||
|
||||
if token_ids_1 is None:
|
||||
return [1] + ([0] * len(token_ids_0)) + [1]
|
||||
return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
|
||||
|
||||
def create_token_type_ids_from_sequences(
|
||||
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
||||
) -> List[int]:
|
||||
"""
|
||||
Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
|
||||
use of token type ids, therefore a list of zeros is returned.
|
||||
|
||||
Args:
|
||||
token_ids_0 (`List[int]`):
|
||||
List of IDs.
|
||||
token_ids_1 (`List[int]`, *optional*):
|
||||
Optional second list of IDs for sequence pairs.
|
||||
|
||||
Returns:
|
||||
`List[int]`: List of zeros.
|
||||
"""
|
||||
eos = [self.eos_token_id]
|
||||
|
||||
if token_ids_1 is None:
|
||||
return len(token_ids_0 + eos) * [0]
|
||||
return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
|
||||
size 1477754
|
||||
179
tokenizer_config.json
Normal file
179
tokenizer_config.json
Normal file
@@ -0,0 +1,179 @@
|
||||
{
|
||||
"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": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92538": {
|
||||
"content": "<|plugin|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92539": {
|
||||
"content": "<|interpreter|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92540": {
|
||||
"content": "<|action_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92541": {
|
||||
"content": "<|action_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92542": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92543": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92544": {
|
||||
"content": "<img>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92545": {
|
||||
"content": "</img>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92546": {
|
||||
"content": "<IMG_CONTEXT>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92547": {
|
||||
"content": "<quad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92548": {
|
||||
"content": "</quad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92549": {
|
||||
"content": "<ref>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92550": {
|
||||
"content": "</ref>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92551": {
|
||||
"content": "<box>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"92552": {
|
||||
"content": "</box>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|action_start|>",
|
||||
"<|action_end|>",
|
||||
"<|interpreter|>",
|
||||
"<|plugin|>",
|
||||
"<img>",
|
||||
"</img>",
|
||||
"<IMG_CONTEXT>",
|
||||
"<quad>",
|
||||
"</quad>",
|
||||
"<ref>",
|
||||
"</ref>",
|
||||
"<box>",
|
||||
"</box>"
|
||||
],
|
||||
"auto_map": {
|
||||
"AutoTokenizer": [
|
||||
"tokenization_internlm2.InternLM2Tokenizer",
|
||||
null
|
||||
]
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "</s>",
|
||||
"tokenizer_class": "InternLM2Tokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user