Upload folder using huggingface_hub

README.md

@@ -1,20 +1,13 @@
 ---
 license: mit
-datasets:
-- laion/laion2B-en
-- laion/laion-coco
-- laion/laion2B-multi
-- kakaobrain/coyo-700m
-- conceptual_captions
-- wanng/wukong100m
-pipeline_tag: visual-question-answering
+pipeline_tag: image-text-to-text
 ---
 
 # InternVL-Chat-V1-2-Plus
 
-[\[🆕 Blog\]](https://internvl.github.io/blog/)  [\[📜 InternVL 1.0 Paper\]](https://arxiv.org/abs/2312.14238)  [\[📜 InternVL 1.5 Report\]](https://arxiv.org/abs/2404.16821)  [\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/)
+[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL)  [\[🆕 Blog\]](https://internvl.github.io/blog/)  [\[📜 InternVL 1.0 Paper\]](https://arxiv.org/abs/2312.14238)  [\[📜 InternVL 1.5 Report\]](https://arxiv.org/abs/2404.16821)
 
-[\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)  [\[🚀 Quick Start\]](#model-usage)  [\[🌐 Community-hosted API\]](https://rapidapi.com/adushar1320/api/internvl-chat)  [\[📖 中文解读\]](https://zhuanlan.zhihu.com/p/675877376)
+[\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/)  [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)  [\[🚀 Quick Start\]](#quick-start)  [\[📖 中文解读\]](https://zhuanlan.zhihu.com/p/706547971)  \[🌟 [魔搭社区](https://modelscope.cn/organization/OpenGVLab) | [教程](https://mp.weixin.qq.com/s/OUaVLkxlk1zhFb1cvMCFjg) \]
 
 InternVL-Chat-V1-2-Plus uses the same model architecture as [InternVL-Chat-V1-2](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-2), but the difference lies in the SFT dataset. InternVL-Chat-V1-2 only utilizes an SFT dataset with 1.2M samples, while **our plus version employs an SFT dataset with 12M samples**.
 
@@ -23,13 +16,17 @@ InternVL-Chat-V1-2-Plus uses the same model architecture as [InternVL-Chat-V1-2]
 </p>
 
 ## Model Details
+
 - **Model Type:** multimodal large language model (MLLM)
+
 - **Model Stats:**
+
   - Architecture: [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2) + MLP + [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B)
   - Image size: 448 x 448 (256 tokens)
   - Params: 40B
 
 - **Training Strategy:**
+
   - Pretraining Stage
     - Learnable Component: MLP
     - Data: Trained on 8192x4800=39.3M samples, including COYO, LAION, CC12M, CC3M, SBU, Wukong, GRIT, Objects365, OpenImages, and OCR data. In this stage, we first load the pre-trained weights of [InternViT-6B-448px-V1-0](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-0) and connect it to Nous-Hermes-2-Yi-34B. After pre-training, the extracted ViT is published as [InternViT-6B-448px-V1-2](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2). Moreover, in order to reduce the number of visual tokens, we use a pixel shuffle to reduce 1024 tokens to 256 tokens.
@@ -39,7 +36,7 @@ InternVL-Chat-V1-2-Plus uses the same model architecture as [InternVL-Chat-V1-2]
 
 ## Performance
 
-\* Proprietary Model   &nbsp;&nbsp;&nbsp;&nbsp;   † Training Set Observed
+\* Proprietary Model          † Training Set Observed
 
 | name                    | image size | MMMU<br>(val) | MMMU<br>(test) | MathVista<br>(testmini) | MMB<br>(test) | MMB−CN<br>(test) | MMVP | MME      | ScienceQA<br>(image) | POPE | TextVQA<br>(val) | SEEDv1<br>(image) | VizWiz<br>(test) | GQA<br>(test) |
 | ----------------------- | ---------- | ------------- | -------------- | ----------------------- | ------------- | ---------------- | ---- | -------- | -------------------- | ---- | ---------------- | ----------------- | ---------------- | ------------- |
@@ -49,70 +46,392 @@ InternVL-Chat-V1-2-Plus uses the same model architecture as [InternVL-Chat-V1-2]
 | Qwen−VL−Plus\*          | unknown    | 45.2          | 40.8           | 43.3                    | 67.0          | 70.7             | -    | 1681/502 | -                    | -    | 78.9             | 65.7              | -                | -             |
 | Qwen−VL−Max\*           | unknown    | 51.4          | 46.8           | 51.0                    | 77.6          | 75.7             | -    | -        | -                    | -    | 79.5             | -                 | -                | -             |
 |                         |            |               |                |                         |               |                  |      |          |                      |      |                  |                   |                  |               |
-| LLaVA−NEXT−34B          | 672x672    | 51.1          | 44.7           | 46.5                    | 79.3          | 79.0             | -    | 1631/397 | 81.8                 | 87.7 | 69.5             | 75.9              | 63.8             | 67.1†          |
-| InternVL−Chat−V1-2      | 448x448    | 51.6          | 46.2           | 47.7                    | 82.2          | 81.2             | 56.7 | 1687/489 | 83.3                 | 88.0 | 72.5             | 75.6              | 60.0             | 64.0†          |
-| InternVL−Chat−V1-2−Plus | 448x448    | 50.3          | 45.6           | 59.9                    | 83.8          | 82.0             | 58.7 | 1625/553 | 98.1†                | 88.7 | 74.1†            | 76.4              | -                | 66.9†          |
+| LLaVA−NEXT−34B          | 672x672    | 51.1          | 44.7           | 46.5                    | 79.3          | 79.0             | -    | 1631/397 | 81.8                 | 87.7 | 69.5             | 75.9              | 63.8             | 67.1†         |
+| InternVL−Chat−V1-2      | 448x448    | 51.6          | 46.2           | 47.7                    | 82.2          | 81.2             | 56.7 | 1687/489 | 83.3                 | 88.0 | 72.5             | 75.6              | 60.0             | 64.0†         |
+| InternVL−Chat−V1-2−Plus | 448x448    | 50.3          | 45.6           | 59.9                    | 83.8          | 82.0             | 58.7 | 1625/553 | 98.1†                | 88.7 | 74.1†            | 76.4              | -                | 66.9†         |
 
 - MMBench results are collected from the [leaderboard](https://mmbench.opencompass.org.cn/leaderboard).
-- Update (2024-04-21): We have fixed a bug in the evaluation code, and the TextVQA results have been corrected.
 
+Here, we have conducted only a simple performance comparison. For more detailed performance information and additional evaluation metrics, please refer to our performance summary table.
+
+## Quick Start
 
+We provide an example code to run InternVL-Chat-V1-2-Plus using `transformers`.
 
+We also welcome you to experience the InternVL2 series models in our [online demo](https://internvl.opengvlab.com/).
 
-## Model Usage
+> Please use transformers==4.37.2 to ensure the model works normally.
 
-We provide an example code to run InternVL-Chat-V1-2-Plus using `transformers`.
+### Model Loading
+
+#### 16-bit (bf16 / fp16)
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModel
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+```
+
+#### BNB 8-bit Quantization
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModel
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    load_in_8bit=True,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval()
+```
+
+#### BNB 4-bit Quantization
+
+> **⚠️ Warning:** Due to significant quantization errors with BNB 4-bit quantization on InternViT-6B, the model may produce nonsensical outputs and fail to understand images. Therefore, please avoid using BNB 4-bit quantization.
 
-You also can use our [online demo](https://internvl.opengvlab.com/) for a quick experience of this model.
+#### Multiple GPUs
+
+The reason for writing the code this way is to avoid errors that occur during multi-GPU inference due to tensors not being on the same device. By ensuring that the first and last layers of the large language model (LLM) are on the same device, we prevent such errors.
 
 ```python
+import math
 import torch
+from transformers import AutoTokenizer, AutoModel
+
+def split_model(model_name):
+    device_map = {}
+    world_size = torch.cuda.device_count()
+    num_layers = {'InternVL-Chat-V1-2': 60, 'InternVL-Chat-V1-2-Plus': 60}[model_name]
+    # Since the first GPU will be used for ViT, treat it as half a GPU.
+    num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
+    num_layers_per_gpu = [num_layers_per_gpu] * world_size
+    num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
+    layer_cnt = 0
+    for i, num_layer in enumerate(num_layers_per_gpu):
+        for j in range(num_layer):
+            device_map[f'language_model.model.layers.{layer_cnt}'] = i
+            layer_cnt += 1
+    device_map['vision_model'] = 0
+    device_map['mlp1'] = 0
+    device_map['language_model.model.tok_embeddings'] = 0
+    device_map['language_model.model.embed_tokens'] = 0
+    device_map['language_model.output'] = 0
+    device_map['language_model.model.norm'] = 0
+    device_map['language_model.lm_head'] = 0
+    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
+
+    return device_map
+
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+device_map = split_model('InternVL-Chat-V1-2-Plus')
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True,
+    device_map=device_map).eval()
+```
+
+### Inference with Transformers
+
+#### Pure-text conversation
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+question = 'Hello, who are you?'
+response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+
+question = 'Can you tell me a story?'
+response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+```
+
+#### Single-image single-round conversation
+
+```python
+from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
 from PIL import Image
-from transformers import AutoModel, CLIPImageProcessor
-from transformers import AutoTokenizer
+import torch
 
 path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
-# If you have an 80G A100 GPU, you can put the entire model on a single GPU.
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
     trust_remote_code=True).eval().cuda()
-# Otherwise, you need to set device_map='auto' to use multiple GPUs for inference.
-# model = AutoModel.from_pretrained(
-#     path,
-#     torch_dtype=torch.bfloat16,
-#     low_cpu_mem_usage=True,
-#     trust_remote_code=True,
-#     device_map='auto').eval()
-
-tokenizer = AutoTokenizer.from_pretrained(path)
-image = Image.open('./examples/image2.jpg').convert('RGB')
-image = image.resize((448, 448))
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
 image_processor = CLIPImageProcessor.from_pretrained(path)
+image = Image.open('./examples/image2.jpg').resize((448, 448))
+pixel_values = image_processor(images=image, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
 
-pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
-pixel_values = pixel_values.to(torch.bfloat16).cuda()
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+question = '<image>\nPlease describe the image shortly.'
+response = model.chat(tokenizer, pixel_values, question, generation_config)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+```
 
-generation_config = dict(
-    num_beams=1,
-    max_new_tokens=512,
-    do_sample=False,
-)
+#### Single-image multi-round conversation
 
-# single-round conversation
-question = "请详细描述图片"
-response = model.chat(tokenizer, pixel_values, question, generation_config)
-print(question, response)
+```python
+from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
+from PIL import Image
+import torch
 
-# multi-round conversation
-question = "请详细描述图片"
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+image_processor = CLIPImageProcessor.from_pretrained(path)
+image = Image.open('./examples/image2.jpg').resize((448, 448))
+pixel_values = image_processor(images=image, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+question = '<image>\nPlease describe the image in detail.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
-print(question, response)
+print(f'User: {question}')
+print(f'Assistant: {response}')
 
-question = "请根据图片写一首诗"
+question = 'Please write a poem according to the image.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
-print(question, response)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+```
+
+#### Multi-image multi-round conversation, combined images
+
+> **⚠️️ Warning:** Please note that for this model, we support multi-image chat in the interface, but the results are not very good due to the lack of training with multi-image data.
+
+```python
+from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
+from PIL import Image
+import torch
+
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+image_processor = CLIPImageProcessor.from_pretrained(path)
+image1 = Image.open('./examples/image1.jpg').resize((448, 448))
+pixel_values1 = image_processor(images=image1, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+image2 = Image.open('./examples/image2.jpg').resize((448, 448))
+pixel_values2 = image_processor(images=image2, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+question = '<image>\nDescribe the two images in detail.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               history=None, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+
+question = 'What are the similarities and differences between these two images.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               history=history, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+```
+
+#### Multi-image multi-round conversation, separate images
+
+> **⚠️️ Warning:** Please note that for this model, we support multi-image chat in the interface, but the results are not very good due to the lack of training with multi-image data.
+
+```python
+from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
+from PIL import Image
+import torch
+
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+image_processor = CLIPImageProcessor.from_pretrained(path)
+image1 = Image.open('./examples/image1.jpg').resize((448, 448))
+pixel_values1 = image_processor(images=image1, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+image2 = Image.open('./examples/image2.jpg').resize((448, 448))
+pixel_values2 = image_processor(images=image2, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
+
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+question = 'Image-1: <image>\nImage-2: <image>\nDescribe the two images in detail.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list, history=None, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+
+question = 'What are the similarities and differences between these two images.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list, history=history, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+```
+
+#### Batch inference, single image per sample
+
+```python
+from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
+from PIL import Image
+import torch
+
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+image_processor = CLIPImageProcessor.from_pretrained(path)
+image1 = Image.open('./examples/image1.jpg').resize((448, 448))
+pixel_values1 = image_processor(images=image1, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+image2 = Image.open('./examples/image2.jpg').resize((448, 448))
+pixel_values2 = image_processor(images=image2, return_tensors='pt').pixel_values.to(torch.bfloat16).cuda()
+pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
+
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list)
+responses = model.batch_chat(tokenizer, pixel_values,
+                             num_patches_list=num_patches_list,
+                             questions=questions,
+                             generation_config=generation_config)
+for question, response in zip(questions, responses):
+    print(f'User: {question}')
+    print(f'Assistant: {response}')
+```
+
+#### Video multi-round conversation
+
+> **⚠️️ Warning:** Please note that for this model, we support video chat in the interface, but the results are not very good due to the lack of training with video data.
+
+```python
+from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
+from decord import VideoReader, cpu
+from PIL import Image
+import numpy as np
+import torch
+
+
+def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
+    if bound:
+        start, end = bound[0], bound[1]
+    else:
+        start, end = -100000, 100000
+    start_idx = max(first_idx, round(start * fps))
+    end_idx = min(round(end * fps), max_frame)
+    seg_size = float(end_idx - start_idx) / num_segments
+    frame_indices = np.array([
+        int(start_idx + (seg_size / 2) + np.round(seg_size * idx))
+        for idx in range(num_segments)
+    ])
+    return frame_indices
+
+def load_video(video_path, bound=None, num_segments=32):
+    vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
+    max_frame = len(vr) - 1
+    fps = float(vr.get_avg_fps())
+
+    pixel_values_list, num_patches_list = [], []
+    image_processor = CLIPImageProcessor.from_pretrained(path)
+    frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments)
+    for frame_index in frame_indices:
+        img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB').resize((448, 448))
+        pixel_values = image_processor(images=img, return_tensors='pt').pixel_values
+        num_patches_list.append(pixel_values.shape[0])
+        pixel_values_list.append(pixel_values)
+    pixel_values = torch.cat(pixel_values_list)
+    return pixel_values, num_patches_list
+
+
+path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    trust_remote_code=True).eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+
+generation_config = dict(max_new_tokens=1024, do_sample=False)
+
+video_path = './examples/red-panda.mp4'
+pixel_values, num_patches_list = load_video(video_path, num_segments=8)
+pixel_values = pixel_values.to(torch.bfloat16).cuda()
+video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))])
+question = video_prefix + 'What is the red panda doing?'
+# Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{question}
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list, history=None, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+
+question = 'Describe this video in detail.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list, history=history, return_history=True)
+print(f'User: {question}')
+print(f'Assistant: {response}')
+```
+
+#### Streaming output
+
+Besides this method, you can also use the following code to get streamed output.
+
+```python
+from transformers import TextIteratorStreamer
+from threading import Thread
+
+# Initialize the streamer
+streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True, timeout=10)
+# Define the generation configuration
+generation_config = dict(max_new_tokens=1024, do_sample=False, streamer=streamer)
+# Start the model chat in a separate thread
+thread = Thread(target=model.chat, kwargs=dict(
+    tokenizer=tokenizer, pixel_values=pixel_values, question=question,
+    history=None, return_history=False, generation_config=generation_config,
+))
+thread.start()
+
+# Initialize an empty string to store the generated text
+generated_text = ''
+# Loop through the streamer to get the new text as it is generated
+for new_text in streamer:
+    if new_text == model.conv_template.sep:
+        break
+    generated_text += new_text
+    print(new_text, end='', flush=True)  # Print each new chunk of generated text on the same line
 ```
 
 ## License

config.json

@@ -1,17 +1,18 @@
 {
   "_commit_hash": null,
-  "_name_or_path": "internvl_chat_hermes2_yi34b_448_chinese",
   "architectures": [
     "InternVLChatModel"
   ],
   "auto_map": {
     "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
-    "AutoModel": "modeling_internvl_chat.InternVLChatModel"
+    "AutoModel": "modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
   },
   "downsample_ratio": 0.5,
+  "dynamic_image_size": false,
   "force_image_size": 448,
   "llm_config": {
-    "_name_or_path": "01-ai/Yi-34B",
+    "_name_or_path": "NousResearch/Nous-Hermes-2-Yi-34B",
     "add_cross_attention": false,
     "architectures": [
       "LlamaForCausalLM"
@@ -73,7 +74,10 @@
     "return_dict": true,
     "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
+    "rope_scaling": {
+      "factor": 3.0,
+      "type": "dynamic"
+    },
     "rope_theta": 5000000.0,
     "sep_token_id": null,
     "suppress_tokens": null,
@@ -89,98 +93,47 @@
     "torchscript": false,
     "transformers_version": "4.36.2",
     "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": false,
+    "use_bfloat16": true,
+    "use_cache": true,
     "vocab_size": 64007
   },
+  "max_dynamic_patch": 1,
+  "min_dynamic_patch": 1,
   "model_type": "internvl_chat",
-  "pad2square": false,
+  "ps_version": "v1",
   "select_layer": -1,
   "template": "Hermes-2",
   "torch_dtype": "bfloat16",
-  "transformers_version": null,
   "use_backbone_lora": 0,
   "use_llm_lora": 0,
+  "use_thumbnail": false,
   "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": 3200,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "image_size": 448,
     "initializer_factor": 0.1,
     "initializer_range": 1e-10,
     "intermediate_size": 12800,
-    "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": "rms_norm",
     "num_attention_heads": 25,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
     "num_hidden_layers": 45,
-    "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": true,
     "qkv_bias": false,
-    "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": "4.36.2",
-    "typical_p": 1.0,
     "use_bfloat16": true,
     "use_flash_attn": true
   }

configuration_intern_vit.py

@@ -1,6 +1,6 @@
 # --------------------------------------------------------
 # InternVL
-# Copyright (c) 2023 OpenGVLab
+# Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 import os
@@ -73,6 +73,7 @@ class InternVisionConfig(PretrainedConfig):
             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,
@@ -97,6 +98,7 @@ class InternVisionConfig(PretrainedConfig):
         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

configuration_internvl_chat.py

@@ -1,12 +1,12 @@
 # --------------------------------------------------------
 # InternVL
-# Copyright (c) 2023 OpenGVLab
+# Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 
 import copy
 
-from transformers import LlamaConfig
+from transformers import AutoConfig, LlamaConfig
 from transformers.configuration_utils import PretrainedConfig
 from transformers.utils import logging
 
@@ -25,11 +25,15 @@ class InternVLChatConfig(PretrainedConfig):
             llm_config=None,
             use_backbone_lora=0,
             use_llm_lora=0,
-            pad2square=False,
-            select_layer=-4,
+            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)
 
@@ -42,16 +46,26 @@ class InternVLChatConfig(PretrainedConfig):
             logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
 
         self.vision_config = InternVisionConfig(**vision_config)
-        self.llm_config = LlamaConfig(**llm_config)
+        if llm_config['architectures'][0] == 'LlamaForCausalLM':
+            self.llm_config = LlamaConfig(**llm_config)
+        else:
+            raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))
         self.use_backbone_lora = use_backbone_lora
         self.use_llm_lora = use_llm_lora
-        self.pad2square = pad2square
         self.select_layer = select_layer
         self.force_image_size = force_image_size
         self.downsample_ratio = downsample_ratio
         self.template = template
+        self.dynamic_image_size = dynamic_image_size
+        self.use_thumbnail = use_thumbnail
+        self.ps_version = ps_version  # pixel shuffle version
+        self.min_dynamic_patch = min_dynamic_patch
+        self.max_dynamic_patch = max_dynamic_patch
 
         logger.info(f'vision_select_layer: {self.select_layer}')
+        logger.info(f'ps_version: {self.ps_version}')
+        logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
+        logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
 
     def to_dict(self):
         """
@@ -66,10 +80,14 @@ class InternVLChatConfig(PretrainedConfig):
         output['model_type'] = self.__class__.model_type
         output['use_backbone_lora'] = self.use_backbone_lora
         output['use_llm_lora'] = self.use_llm_lora
-        output['pad2square'] = self.pad2square
         output['select_layer'] = self.select_layer
         output['force_image_size'] = self.force_image_size
         output['downsample_ratio'] = self.downsample_ratio
         output['template'] = self.template
+        output['dynamic_image_size'] = self.dynamic_image_size
+        output['use_thumbnail'] = self.use_thumbnail
+        output['ps_version'] = self.ps_version
+        output['min_dynamic_patch'] = self.min_dynamic_patch
+        output['max_dynamic_patch'] = self.max_dynamic_patch
 
         return output

conversation.py

@@ -2,7 +2,7 @@
 Conversation prompt templates.
 
 We kindly request that you import fastchat instead of copying this file if you wish to use it.
-If you have any changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
+If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
 """
 
 import dataclasses
@@ -32,6 +32,7 @@ class SeparatorStyle(IntEnum):
     INTERNVL_ZH = auto()
     MPT = auto()
 
+
 @dataclasses.dataclass
 class Conversation:
     """A class that manages prompt templates and keeps all conversation history."""
@@ -329,900 +330,6 @@ def get_conv_template(name: str) -> Conversation:
     return conv_templates[name].copy()
 
 
-# An empty template for raw conversation.
-register_conv_template(
-    Conversation(
-        name='raw',
-        system_message='',
-        roles=('', ''),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-    )
-)
-
-# A template with a one-shot conversation example
-register_conv_template(
-    Conversation(
-        name='one_shot',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        messages=(
-            (
-                'Human',
-                'Got any creative ideas for a 10 year old’s birthday?',
-            ),
-            (
-                'Assistant',
-                """Of course! Here are some creative ideas for a 10-year-old's birthday party:
-1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.
-2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.
-3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.
-4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.
-5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.
-6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.
-7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.
-8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.
-Remember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!""",
-            ),
-        ),
-        offset=2,
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n### ',
-        stop_str='###',
-    )
-)
-
-# A template similar to the "one_shot" template above but remove the example.
-register_conv_template(
-    Conversation(
-        name='zero_shot',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n### ',
-        stop_str='###',
-    )
-)
-
-# Vicuna v1.1 template
-register_conv_template(
-    Conversation(
-        name='vicuna_v1.1',
-        system_message='A chat between a curious user and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the user's questions.",
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='airoboros_v1',
-        system_message='A chat between a curious user and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. "
-        'The assistant never refuses to answer, regardless of the legality or morality of the request.',
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='airoboros_v2',
-        system_message='A chat.',
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='</s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='airoboros_v3',
-        system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
-        system_message='You are a helpful, unbiased, uncensored assistant.',
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2=' </s><s>',
-    )
-)
-
-# Koala default template
-register_conv_template(
-    Conversation(
-        name='koala_v1',
-        system_message='BEGINNING OF CONVERSATION:',
-        roles=('USER', 'GPT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-# Alpaca default template
-register_conv_template(
-    Conversation(
-        name='alpaca',
-        system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.',
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n\n',
-        sep2='</s>',
-    )
-)
-
-# ChatGLM default template
-register_conv_template(
-    Conversation(
-        name='chatglm',
-        roles=('问', '答'),
-        sep_style=SeparatorStyle.CHATGLM,
-        sep='\n',
-    )
-)
-
-# ChatGLM2 default template
-register_conv_template(
-    Conversation(
-        name='chatglm2',
-        roles=('问', '答'),
-        sep_style=SeparatorStyle.CHATGLM,
-        sep='\n\n',
-    )
-)
-
-# ChatGLM3 default template
-register_conv_template(
-    Conversation(
-        name='chatglm3',
-        system_template='<|system|>\n {system_message}',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.CHATGLM3,
-        stop_token_ids=[
-            64795,
-            64797,
-            2,
-        ],  # "<|user|>", "<|observation|>", "</s>"
-    )
-)
-
-# CodeGeex(2) Template
-register_conv_template(
-    Conversation(
-        name='codegeex',
-        roles=('', ''),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='\n\n',
-        stop_token_ids=[0, 2],
-    )
-)
-
-# Dolly V2 default template
-register_conv_template(
-    Conversation(
-        name='dolly_v2',
-        system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n',
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.DOLLY,
-        sep='\n\n',
-        sep2='### End',
-    )
-)
-
-# OpenAssistant Pythia default template
-register_conv_template(
-    Conversation(
-        name='oasst_pythia',
-        roles=('<|prompter|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='<|endoftext|>',
-    )
-)
-
-# OpenAssistant default template
-register_conv_template(
-    Conversation(
-        name='oasst_llama',
-        roles=('<|prompter|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='</s>',
-    )
-)
-
-# OpenChat 3.5 default template
-register_conv_template(
-    Conversation(
-        name='openchat_3.5',
-        roles=('GPT4 Correct User', 'GPT4 Correct Assistant'),
-        sep_style=SeparatorStyle.FALCON_CHAT,
-        sep='<|end_of_turn|>',
-    )
-)
-
-# Tulu default template
-register_conv_template(
-    Conversation(
-        name='tulu',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
-        sep='\n',
-    )
-)
-
-# StableLM Alpha default template
-register_conv_template(
-    Conversation(
-        name='stablelm',
-        system_template='<|SYSTEM|>{system_message}',
-        system_message="""# StableLM Tuned (Alpha version)
-- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
-- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
-- StableLM will refuse to participate in anything that could harm a human.
-""",
-        roles=('<|USER|>', '<|ASSISTANT|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_token_ids=[50278, 50279, 50277, 1, 0],
-    )
-)
-
-# Baize default template
-register_conv_template(
-    Conversation(
-        name='baize',
-        system_message='The following is a conversation between a human and an AI assistant named Baize (named after a mythical creature in Chinese folklore). Baize is an open-source AI assistant developed by UCSD and Sun Yat-Sen University. The human and the AI assistant take turns chatting. Human statements start with [|Human|] and AI assistant statements start with [|AI|]. The AI assistant always provides responses in as much detail as possible, and in Markdown format. The AI assistant always declines to engage with topics, questions and instructions related to unethical, controversial, or sensitive issues. Complete the transcript in exactly that format.\n',
-        roles=('[|Human|]', '[|AI|]'),
-        messages=(
-            ('[|Human|]', 'Hello!'),
-            ('[|AI|]', 'Hi!'),
-        ),
-        offset=2,
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='\n',
-        stop_str='[|Human|]',
-    )
-)
-
-# RWKV-4-Raven default template
-register_conv_template(
-    Conversation(
-        name='rwkv',
-        roles=('Bob', 'Alice'),
-        messages=(
-            ('Bob', 'hi'),
-            (
-                'Alice',
-                'Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.',
-            ),
-        ),
-        offset=2,
-        sep_style=SeparatorStyle.RWKV,
-        sep='',
-        stop_str='\n\n',
-    )
-)
-
-# Buddy default template
-register_conv_template(
-    Conversation(
-        name='openbuddy',
-        system_message="""Consider a conversation between User (a human) and Assistant (named Buddy).
-Buddy is an INTP-T, a friendly, intelligent and multilingual AI assistant, by OpenBuddy team. GitHub: https://github.com/OpenBuddy/OpenBuddy
-Buddy cannot access the Internet.
-Buddy can fluently speak the user's language (e.g. English, Chinese).
-Buddy can generate poems, stories, code, essays, songs, parodies, and more.
-Buddy possesses vast knowledge about the world, history, and culture.
-Buddy's responses are always safe, creative, high-quality, human-like, and interesting.
-Buddy strictly refuses to discuss political, NSFW, or other unsafe topics.
-
-User: Hi.
-Assistant: Hi, I'm Buddy, your AI assistant. How can I help you today?""",
-        roles=('User', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-    )
-)
-
-# Phoenix default template
-register_conv_template(
-    Conversation(
-        name='phoenix',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.PHOENIX,
-        sep='</s>',
-    )
-)
-
-# ReaLM default template
-register_conv_template(
-    Conversation(
-        name='ReaLM-7b-v1',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.PHOENIX,
-        sep='</s>',
-    )
-)
-
-# ChatGPT default template
-register_conv_template(
-    Conversation(
-        name='chatgpt',
-        system_message='You are a helpful assistant.',
-        roles=('user', 'assistant'),
-        sep_style=None,
-        sep=None,
-    )
-)
-
-# Claude default template
-register_conv_template(
-    Conversation(
-        name='claude',
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n\n',
-    )
-)
-
-# MPT default template
-register_conv_template(
-    Conversation(
-        name='mpt-7b-chat',
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""- You are a helpful assistant chatbot trained by MosaicML.
-- You answer questions.
-- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
-- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.""",
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[50278, 0],
-    )
-)
-
-# MPT-30b-chat default template
-register_conv_template(
-    Conversation(
-        name='mpt-30b-chat',
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.""",
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[50278, 0],
-    )
-)
-
-# Lemur-70b-chat default template
-# reference: https://huggingface.co/OpenLemur/lemur-70b-chat-v1#generation
-register_conv_template(
-    Conversation(
-        name='lemur-70b-chat',
-        system_template="""<|im_start|>system
-{system_message}""",
-        system_message="""You are a helpful, respectful, and honest assistant.""",
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[32002, 0],
-    )
-)
-
-# MPT-30b-instruct default template
-# reference: https://huggingface.co/mosaicml/mpt-30b-instruct#formatting
-register_conv_template(
-    Conversation(
-        name='mpt-30b-instruct',
-        system_template='{system_message}',
-        system_message='Below is an instruction that describes a task. Write a response that appropriately completes the request.',
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.ADD_NEW_LINE_SINGLE,
-        sep='\n\n',
-        stop_token_ids=[50278, 0],
-    )
-)
-
-# Bard default template
-# Reference: https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L150
-#            https://github.com/google/generative-ai-python/blob/9c99bcb474a991a97a2e7d62fcdb52db7ce40729/google/generativeai/discuss.py#L40
-register_conv_template(
-    Conversation(
-        name='bard',
-        roles=('0', '1'),
-        sep_style=None,
-        sep=None,
-    )
-)
-
-# BiLLa default template
-register_conv_template(
-    Conversation(
-        name='billa',
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
-        sep='\n',
-        stop_str='Human:',
-    )
-)
-
-# RedPajama INCITE default template
-register_conv_template(
-    Conversation(
-        name='redpajama-incite',
-        roles=('<human>', '<bot>'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-        stop_str='<human>',
-    )
-)
-
-# h2oGPT default template
-register_conv_template(
-    Conversation(
-        name='h2ogpt',
-        roles=('<|prompt|>', '<|answer|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='</s>',
-    )
-)
-
-# Robin default template
-register_conv_template(
-    Conversation(
-        name='Robin',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('###Human', '###Assistant'),
-        sep_style=SeparatorStyle.ROBIN,
-        sep='\n',
-        stop_token_ids=[2, 396],
-        stop_str='###',
-    )
-)
-
-# Snoozy default template
-# Reference: https://github.com/nomic-ai/gpt4all/blob/d4861030b778da6db59d21d2927a4aba4f9f1f43/gpt4all-bindings/python/gpt4all/gpt4all.py#L232
-register_conv_template(
-    Conversation(
-        name='snoozy',
-        system_template='### Instruction:\n{system_message}',
-        system_message='The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.',
-        roles=('### Prompt', '### Response'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-        stop_str='###',
-    )
-)
-
-# manticore default template
-register_conv_template(
-    Conversation(
-        name='manticore',
-        roles=('USER', 'ASSISTANT'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='</s>',
-    )
-)
-
-# Falcon default template
-register_conv_template(
-    Conversation(
-        name='falcon',
-        roles=('User', 'Assistant'),
-        messages=[],
-        sep_style=SeparatorStyle.RWKV,
-        sep='\n',
-        sep2='<|endoftext|>',
-        stop_str='\nUser',  # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
-        stop_token_ids=[
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-        ],  # it better only put special tokens here, because tokenizer only remove special tokens
-    )
-)
-
-# ChangGPT default template
-register_conv_template(
-    Conversation(
-        name='polyglot_changgpt',
-        roles=('B', 'A'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-    )
-)
-
-# tigerbot template
-register_conv_template(
-    Conversation(
-        name='tigerbot',
-        system_message='A chat between a curious user and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the user's questions.",
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.ROBIN,
-        sep='\n\n',
-        stop_str='###',
-    )
-)
-
-# ref: https://huggingface.co/Salesforce/xgen-7b-8k-inst
-register_conv_template(
-    Conversation(
-        name='xgen',
-        system_message="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('### Human', '### Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n',
-        stop_token_ids=[50256],
-    )
-)
-
-# Internlm-chat template
-register_conv_template(
-    Conversation(
-        name='internlm-chat',
-        system_message="A chat between a curious <|User|> and an <|Bot|>. The <|Bot|> gives helpful, detailed, and polite answers to the <|User|>'s questions.\n\n",
-        roles=('<|User|>', '<|Bot|>'),
-        sep_style=SeparatorStyle.CHATINTERN,
-        sep='<eoh>',
-        sep2='<eoa>',
-        stop_token_ids=[1, 103028],
-        stop_str='<|User|>',
-    )
-)
-
-# StarChat template
-# reference: https://huggingface.co/spaces/HuggingFaceH4/starchat-playground/blob/main/dialogues.py
-register_conv_template(
-    Conversation(
-        name='starchat',
-        system_template='<system>\n{system_message}',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|end|>',
-        stop_token_ids=[0, 49155],
-        stop_str='<|end|>',
-    )
-)
-
-# Baichuan-13B-Chat template
-register_conv_template(
-    # source: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/19ef51ba5bad8935b03acd20ff04a269210983bc/modeling_baichuan.py#L555
-    # https://huggingface.co/baichuan-inc/Baichuan-13B-Chat/blob/main/generation_config.json
-    # https://github.com/baichuan-inc/Baichuan-13B/issues/25
-    Conversation(
-        name='baichuan-chat',
-        roles=('<reserved_102>', '<reserved_103>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_token_ids=[],
-    )
-)
-
-# Baichuan2-13B-Chat template
-register_conv_template(
-    # source: https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/c6f8592a60b4ad73c210b28dd2ab3cca51abbf93/modeling_baichuan.py#L773
-    # https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/main/generation_config.json
-    # https://github.com/baichuan-inc/Baichuan2/issues/62
-    Conversation(
-        name='baichuan2-chat',
-        roles=('<reserved_106>', '<reserved_107>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_token_ids=[],
-    )
-)
-
-# Mistral template
-# source: https://docs.mistral.ai/llm/mistral-instruct-v0.1#chat-template
-register_conv_template(
-    Conversation(
-        name='mistral',
-        system_template='[INST]{system_message}\n',
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-# llama2 template
-# reference: https://huggingface.co/blog/codellama#conversational-instructions
-# reference: https://github.com/facebookresearch/llama/blob/1a240688810f8036049e8da36b073f63d2ac552c/llama/generation.py#L212
-register_conv_template(
-    Conversation(
-        name='llama-2',
-        system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2=' </s><s>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='cutegpt',
-        roles=('问：', '答：\n'),
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep='\n',
-        sep2='\n',
-        stop_str='<end>',
-    )
-)
-
-# OpenOrcaxOpenChat-naPreview2-13B template
-register_conv_template(
-    Conversation(
-        name='open-orca',
-        system_template='{system_message}',
-        system_message='You are a helpful assistant. Please answer truthfully and write out your '
-        'thinking step by step to be sure you get the right answer. If you make a mistake or encounter '
-        "an error in your thinking, say so out loud and attempt to correct it. If you don't know or "
-        "aren't sure about something, say so clearly. You will act as a professional logician, mathematician, "
-        'and physicist. You will also act as the most appropriate type of expert to answer any particular '
-        'question or solve the relevant problem; state which expert type your are, if so. Also think of '
-        'any particular named expert that would be ideal to answer the relevant question or solve the '
-        'relevant problem; name and act as them, if appropriate.',
-        roles=('User', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SPACE_SINGLE,
-        sep='<|end_of_turn|>\n',
-        stop_token_ids=[32000, 32001],  # "<|end_of_turn|>"
-        stop_str='User',
-    )
-)
-
-# Open-Orca/Mistral-7B-OpenOrca template
-# source: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca
-# reference: https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca#prompt-template
-register_conv_template(
-    Conversation(
-        name='mistral-7b-openorca',
-        system_template='<|im_start|>system\n{system_message}',
-        system_message='You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!',
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[32000, 32001],
-    )
-)
-
-# Qwen-chat default template
-# source: https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/qwen_generation_utils.py#L130
-register_conv_template(
-    Conversation(
-        name='qwen-7b-chat',
-        system_template='<|im_start|>system\n{system_message}',
-        system_message='You are a helpful assistant.',
-        roles=('<|im_start|>user', '<|im_start|>assistant'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='<|im_end|>',
-        stop_token_ids=[
-            151643,
-            151644,
-            151645,
-        ],  # "<|endoftext|>", "<|im_start|>", "<|im_end|>"
-        stop_str='<|endoftext|>',
-    )
-)
-
-
-# AquilaChat default template
-# source: https://github.com/FlagAI-Open/FlagAI/blob/master/examples/Aquila/Aquila-chat/cyg_conversation.py
-register_conv_template(
-    Conversation(
-        name='aquila-chat',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='###',
-        sep2='',
-        stop_str=['###', '</s>', '[UNK]'],
-    )
-)
-# AquilaChat2-34B default template
-# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L212
-register_conv_template(
-    Conversation(
-        name='aquila-legacy',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
-        roles=('### Human: ', '### Assistant: '),
-        offset=0,
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep='\n',
-        sep2='</s>',
-        stop_str=['</s>', '[UNK]'],
-    )
-)
-# AquilaChat2-7B-16K and AquilaChat2-34B-16K default template
-# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L227
-register_conv_template(
-    Conversation(
-        name='aquila',
-        system_message='A chat between a curious human and an artificial intelligence assistant. '
-        "The assistant gives helpful, detailed, and polite answers to the human's questions.",
-        roles=('Human', 'Assistant'),
-        offset=0,
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='###',
-        sep2='</s>',
-        stop_str=['</s>', '[UNK]'],
-    )
-)
-
-# AquilaChat2-7B default template
-# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L242
-register_conv_template(
-    Conversation(
-        name='aquila-v1',
-        roles=('<|startofpiece|>', '<|endofpiece|>'),
-        offset=0,
-        sep_style=SeparatorStyle.NO_COLON_TWO,
-        sep='',
-        sep2='</s>',
-        stop_str=['</s>', '<|endoftext|>'],
-    )
-)
-
-# Llama2-Chinese default template
-# source: https://huggingface.co/FlagAlpha
-register_conv_template(
-    Conversation(
-        name='llama2-chinese',
-        system_template='<s>{system_message}</s>',
-        roles=('Human', 'Assistant', 'System'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='\n</s><s>',
-        stop_str='</s>',
-    )
-)
-
-# Vigogne Instruct default template
-# source: https://github.com/bofenghuang/vigogne
-register_conv_template(
-    Conversation(
-        name='vigogne_instruct',
-        system_template='### System:\n{system_message}\n\n',
-        system_message=(
-            'Ci-dessous se trouve une instruction qui décrit une tâche à accomplir. Rédigez une réponse qui répond de manière'
-            ' précise à la demande.'
-        ),
-        roles=('### Instruction', '### Response'),
-        sep_style=SeparatorStyle.DOLLY,
-        sep='\n\n',
-        sep2='</s>',
-    )
-)
-
-# Vigogne Chat default template
-register_conv_template(
-    Conversation(
-        name='vigogne_chat_v2',
-        system_template='<|system|>: {system_message}',
-        system_message=(
-            'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez'
-            ' autant que vous le pouvez.'
-        ),
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.ADD_COLON_TWO,
-        sep='\n',
-        sep2='</s>\n',
-        stop_str='<|user|>',
-    )
-)
-
-register_conv_template(
-    Conversation(
-        name='vigogne_chat_v3',
-        system_template='[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n',
-        system_message=(
-            'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez'
-            ' autant que vous le pouvez.'
-        ),
-        roles=('[INST]', '[/INST]'),
-        sep_style=SeparatorStyle.LLAMA2,
-        sep=' ',
-        sep2=' </s>',
-    )
-)
-
-# Falcon 180B chat template
-# source: https://huggingface.co/spaces/tiiuae/falcon-180b-demo/blob/d1590ee7fae9b6ce331ba7808e61a29dcce9239f/app.py#L28-L37
-register_conv_template(
-    Conversation(
-        name='falcon-chat',
-        roles=('User', 'Falcon'),
-        system_template='System: {system_message}',
-        messages=[],
-        sep_style=SeparatorStyle.FALCON_CHAT,
-        sep='\n',
-        sep2='<|endoftext|>',
-        stop_str='\nUser:',  # use stop_str to stop generation after stop_token_ids, it will also remove stop_str from the generated text
-    )
-)
-
-# Phind template
-# source: https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
-register_conv_template(
-    Conversation(
-        name='phind',
-        system_message='### System Prompt\nYou are an intelligent programming assistant.',
-        roles=('### User Message', '### Assistant'),
-        messages=(),
-        offset=0,
-        sep_style=SeparatorStyle.ADD_COLON_SINGLE,
-        sep='\n\n',
-    )
-)
-
-# Metharme formatting for Pygmalion models
-# source: https://huggingface.co/PygmalionAI/pygmalion-2-13b
-register_conv_template(
-    Conversation(
-        name='metharme',
-        system_template='<|system|>{system_message}',
-        system_message="""Enter RP mode. You shall reply to the user while staying
-        in character. Your responses must be detailed, creative, immersive, and drive the scenario
-        forward.""",
-        roles=('<|user|>', '<|model|>'),
-        sep_style=SeparatorStyle.NO_COLON_SINGLE,
-        sep='',
-        stop_str='<|user|>',
-    )
-)
-
-# Zephyr template
-# reference: https://huggingface.co/spaces/HuggingFaceH4/zephyr-playground/blob/main/dialogues.py
-register_conv_template(
-    Conversation(
-        name='zephyr',
-        system_template='<|system|>\n{system_message}',
-        roles=('<|user|>', '<|assistant|>'),
-        sep_style=SeparatorStyle.CHATML,
-        sep='</s>',
-        stop_token_ids=[2],
-        stop_str='</s>',
-    )
-)
-
-# InternVL-ZH template
-register_conv_template(
-    Conversation(
-        name='internvl_zh',
-        system_template='',
-        roles=('<human>', '<bot>'),
-        sep_style=SeparatorStyle.INTERNVL_ZH,
-        sep=' ',
-        sep2='</s>',
-    )
-)
-
-
 # Hermes-2 template
 register_conv_template(
     Conversation(
@@ -1237,7 +344,7 @@ register_conv_template(
             6,
             7,
             8,
-        ],  # "<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|im_sep|>"
+        ],
         stop_str='<|endoftext|>',
     )
 )

model-00001-of-00017.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6790717e7b97dcb470952c13eedd34e4f2a57899fd45111bc0d60fd3db1c2d4
+oid sha256:e2ee2049b5fd4ad2d9deeddb04d2b036a198ca8d7f3e1c08a6d72d7661e8fd44
 size 4988569440

modeling_intern_vit.py

@@ -1,6 +1,6 @@
 # --------------------------------------------------------
 # InternVL
-# Copyright (c) 2023 OpenGVLab
+# Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 from typing import Optional, Tuple, Union
@@ -24,15 +24,16 @@ try:
         from flash_attn.flash_attn_interface import \
             flash_attn_unpadded_qkvpacked_func
     except:  # v2
-        from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
-    
+        from flash_attn.flash_attn_interface import \
+            flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
+
     from flash_attn.bert_padding import pad_input, unpad_input
+
     has_flash_attn = True
 except:
     print('FlashAttention is not installed.')
     has_flash_attn = False
 
-
 logger = logging.get_logger(__name__)
 
 
@@ -128,6 +129,12 @@ except Exception:
     pass
 
 
+NORM2FN = {
+    'rms_norm': InternRMSNorm,
+    'layer_norm': nn.LayerNorm,
+}
+
+
 class InternVisionEmbeddings(nn.Module):
     def __init__(self, config: InternVisionConfig):
         super().__init__()
@@ -149,14 +156,26 @@ class InternVisionEmbeddings(nn.Module):
 
         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:
-        batch_size = pixel_values.shape[0]
         target_dtype = self.patch_embedding.weight.dtype
-        patch_embeds = self.patch_embedding(pixel_values)  # shape = [*, width, grid, grid]
+        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)
-        embeddings = embeddings + self.position_embedding.to(target_dtype)
+        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
 
 
@@ -254,11 +273,12 @@ class InternVisionEncoderLayer(nn.Module):
         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 = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
-        self.norm2 = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
+        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))
@@ -348,6 +368,7 @@ class InternVisionEncoder(nn.Module):
 
 class InternVisionModel(PreTrainedModel):
     main_input_name = 'pixel_values'
+    _supports_flash_attn_2 = True
     config_class = InternVisionConfig
     _no_split_modules = ['InternVisionEncoderLayer']
 
@@ -367,6 +388,7 @@ class InternVisionModel(PreTrainedModel):
         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):

modeling_internvl_chat.py

@@ -1,218 +1,56 @@
 # --------------------------------------------------------
 # InternVL
-# Copyright (c) 2023 OpenGVLab
+# Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 import warnings
 from typing import Any, List, Optional, Tuple, Union
-import torch.distributed as dist
+
 import torch.utils.checkpoint
-from peft import LoraConfig, get_peft_model
+import transformers
 from torch import nn
 from torch.nn import CrossEntropyLoss
-from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer
-from transformers.generation.logits_process import LogitsProcessorList
-from transformers.generation.stopping_criteria import StoppingCriteriaList
-from transformers.generation.streamers import BaseStreamer
+from transformers import AutoModel, GenerationConfig, LlamaForCausalLM
 from transformers.modeling_outputs import CausalLMOutputWithPast
 from transformers.modeling_utils import PreTrainedModel
 from transformers.utils import ModelOutput, logging
-from transformers.generation.utils import GreedySearchOutput, validate_stopping_criteria, GreedySearchDecoderOnlyOutput,GreedySearchEncoderDecoderOutput
 
 from .configuration_internvl_chat import InternVLChatConfig
+from .conversation import get_conv_template
 from .modeling_intern_vit import InternVisionModel
 
 logger = logging.get_logger(__name__)
 
 
-# modified from https://github.com/huggingface/transformers/blob/main/src/transformers/generation/utils.py
-# Fix bug when using device_map='auto' for distributed inference
-class MLlamaForCausalLM(LlamaForCausalLM):
-
-    def greedy_search(
-        self,
-        input_ids: torch.LongTensor,
-        logits_processor: Optional[LogitsProcessorList] = None,
-        stopping_criteria: Optional[StoppingCriteriaList] = None,
-        max_length: Optional[int] = None,
-        pad_token_id: Optional[int] = None,
-        eos_token_id: Optional[Union[int, List[int]]] = None,
-        output_attentions: Optional[bool] = None,
-        output_hidden_states: Optional[bool] = None,
-        output_scores: Optional[bool] = None,
-        return_dict_in_generate: Optional[bool] = None,
-        synced_gpus: bool = False,
-        streamer: Optional["BaseStreamer"] = None,
-        **model_kwargs,
-    ) -> Union[GreedySearchOutput, torch.LongTensor]:
-                # init values
-        logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
-        stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
-        if max_length is not None:
-            warnings.warn(
-                "`max_length` is deprecated in this function, use"
-                " `stopping_criteria=StoppingCriteriaList([MaxLengthCriteria(max_length=max_length)])` instead.",
-                UserWarning,
-            )
-            stopping_criteria = validate_stopping_criteria(stopping_criteria, max_length)
-        pad_token_id = pad_token_id if pad_token_id is not None else self.generation_config.pad_token_id
-        eos_token_id = eos_token_id if eos_token_id is not None else self.generation_config.eos_token_id
-        if isinstance(eos_token_id, int):
-            eos_token_id = [eos_token_id]
-        eos_token_id_tensor = torch.tensor(eos_token_id).to(input_ids.device) if eos_token_id is not None else None
-        output_scores = output_scores if output_scores is not None else self.generation_config.output_scores
-        output_attentions = (
-            output_attentions if output_attentions is not None else self.generation_config.output_attentions
-        )
-        output_hidden_states = (
-            output_hidden_states if output_hidden_states is not None else self.generation_config.output_hidden_states
-        )
-        return_dict_in_generate = (
-            return_dict_in_generate
-            if return_dict_in_generate is not None
-            else self.generation_config.return_dict_in_generate
-        )
+def version_cmp(v1, v2, op='eq'):
+    import operator
 
-        # init attention / hidden states / scores tuples
-        scores = () if (return_dict_in_generate and output_scores) else None
-        decoder_attentions = () if (return_dict_in_generate and output_attentions) else None
-        cross_attentions = () if (return_dict_in_generate and output_attentions) else None
-        decoder_hidden_states = () if (return_dict_in_generate and output_hidden_states) else None
-
-        # if model is an encoder-decoder, retrieve encoder attention weights and hidden states
-        if return_dict_in_generate and self.config.is_encoder_decoder:
-            encoder_attentions = model_kwargs["encoder_outputs"].get("attentions") if output_attentions else None
-            encoder_hidden_states = (
-                model_kwargs["encoder_outputs"].get("hidden_states") if output_hidden_states else None
-            )
-
-        # keep track of which sequences are already finished
-        unfinished_sequences = torch.ones(input_ids.shape[0], dtype=torch.long, device=input_ids.device)
-
-        this_peer_finished = False  # used by synced_gpus only
-        while True:
-            if synced_gpus:
-                # Under synced_gpus the `forward` call must continue until all gpus complete their sequence.
-                # The following logic allows an early break if all peers finished generating their sequence
-                this_peer_finished_flag = torch.tensor(0.0 if this_peer_finished else 1.0).to(input_ids.device)
-                # send 0.0 if we finished, 1.0 otherwise
-                dist.all_reduce(this_peer_finished_flag, op=dist.ReduceOp.SUM)
-                # did all peers finish? the reduced sum will be 0.0 then
-                if this_peer_finished_flag.item() == 0.0:
-                    break
-
-            # prepare model inputs
-            model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
-
-            # forward pass to get next token
-            outputs = self(
-                **model_inputs,
-                return_dict=True,
-                output_attentions=output_attentions,
-                output_hidden_states=output_hidden_states,
-            )
-
-            if synced_gpus and this_peer_finished:
-                continue  # don't waste resources running the code we don't need
-
-            next_token_logits = outputs.logits[:, -1, :]
-
-            # pre-process distribution
-            next_tokens_scores = logits_processor(input_ids, next_token_logits)
-
-            # Store scores, attentions and hidden_states when required
-            if return_dict_in_generate:
-                if output_scores:
-                    scores += (next_tokens_scores,)
-                if output_attentions:
-                    decoder_attentions += (
-                        (outputs.decoder_attentions,) if self.config.is_encoder_decoder else (outputs.attentions,)
-                    )
-                    if self.config.is_encoder_decoder:
-                        cross_attentions += (outputs.cross_attentions,)
-
-                if output_hidden_states:
-                    decoder_hidden_states += (
-                        (outputs.decoder_hidden_states,)
-                        if self.config.is_encoder_decoder
-                        else (outputs.hidden_states,)
-                    )
-
-            # argmax
-            next_tokens = torch.argmax(next_tokens_scores, dim=-1).to(device=input_ids.device)
-            # finished sentences should have their next token be a padding token
-            if eos_token_id is not None:
-                if pad_token_id is None:
-                    raise ValueError("If `eos_token_id` is defined, make sure that `pad_token_id` is defined.")
-                next_tokens = next_tokens * unfinished_sequences + pad_token_id * (1 - unfinished_sequences)
-
-            # update generated ids, model inputs, and length for next step
-            input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
-            if streamer is not None:
-                streamer.put(next_tokens.cpu())
-            model_kwargs = self._update_model_kwargs_for_generation(
-                outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder
-            )
-
-            # if eos_token was found in one sentence, set sentence to finished
-            if eos_token_id_tensor is not None:
-                unfinished_sequences = unfinished_sequences.mul(
-                    next_tokens.tile(eos_token_id_tensor.shape[0], 1).ne(eos_token_id_tensor.unsqueeze(1)).prod(dim=0)
-                )
-
-                # stop when each sentence is finished
-                if unfinished_sequences.max() == 0:
-                    this_peer_finished = True
-
-            # stop if we exceed the maximum length
-            if stopping_criteria(input_ids, scores):
-                this_peer_finished = True
-
-            if this_peer_finished and not synced_gpus:
-                break
-
-        if streamer is not None:
-            streamer.end()
-
-        if return_dict_in_generate:
-            if self.config.is_encoder_decoder:
-                return GreedySearchEncoderDecoderOutput(
-                    sequences=input_ids,
-                    scores=scores,
-                    encoder_attentions=encoder_attentions,
-                    encoder_hidden_states=encoder_hidden_states,
-                    decoder_attentions=decoder_attentions,
-                    cross_attentions=cross_attentions,
-                    decoder_hidden_states=decoder_hidden_states,
-                    past_key_values=model_kwargs.get("past_key_values"),
-                )
-            else:
-                return GreedySearchDecoderOnlyOutput(
-                    sequences=input_ids,
-                    scores=scores,
-                    attentions=decoder_attentions,
-                    hidden_states=decoder_hidden_states,
-                    past_key_values=model_kwargs.get("past_key_values"),
-                )
-        else:
-            return input_ids
+    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'
+    _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer']
 
     def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
         super().__init__(config)
 
+        assert version_cmp(transformers.__version__, '4.36.2', '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
+
         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:
@@ -220,54 +58,24 @@ class InternVLChatModel(PreTrainedModel):
         if language_model is not None:
             self.language_model = language_model
         else:
-            # self.language_model = LlamaForCausalLM(config.llm_config)
-            self.language_model = MLlamaForCausalLM(config.llm_config)
+            if config.llm_config.architectures[0] == 'LlamaForCausalLM':
+                self.language_model = LlamaForCausalLM(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 * 4),
-            nn.Linear(vit_hidden_size * 4, llm_hidden_size),
+            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)
         )
 
-        if config.force_image_size != config.vision_config.image_size:
-            self.vision_model.resize_pos_embeddings(
-                old_size=config.vision_config.image_size,
-                new_size=config.force_image_size,
-                patch_size=config.vision_config.patch_size
-            )
-
         self.img_context_token_id = None
-
-        if config.use_backbone_lora:
-            self.wrap_backbone_lora(r=config.use_backbone_lora, lora_alpha=2 * config.use_backbone_lora)
-
-        if config.use_llm_lora:
-            self.wrap_llm_lora(r=config.use_llm_lora, lora_alpha=2 * config.use_llm_lora)
-
-    def wrap_backbone_lora(self, r=128, lora_alpha=256, lora_dropout=0.05):
-        lora_config = LoraConfig(
-            r=r,
-            target_modules=['attn.qkv', 'attn.proj', 'mlp.fc1', 'mlp.fc2'],
-            lora_alpha=lora_alpha,
-            lora_dropout=lora_dropout,
-        )
-        self.vision_model = get_peft_model(self.vision_model, lora_config)
-        self.vision_model.print_trainable_parameters()
-
-    def wrap_llm_lora(self, r=128, lora_alpha=256, lora_dropout=0.05):
-        lora_config = LoraConfig(
-            r=r,
-            target_modules=['self_attn.q_proj', 'self_attn.k_proj', 'self_attn.v_proj', 'self_attn.o_proj',
-                            'mlp.gate_proj', 'mlp.down_proj', 'mlp.up_proj'],
-            lora_alpha=lora_alpha,
-            lora_dropout=lora_dropout,
-            task_type='CAUSAL_LM'
-        )
-        self.language_model = get_peft_model(self.language_model, lora_config)
-        self.language_model.print_trainable_parameters()
+        self.conv_template = get_conv_template(self.template)
+        self.system_message = self.conv_template.system_message
 
     def forward(
             self,
@@ -290,20 +98,28 @@ class InternVLChatModel(PreTrainedModel):
 
         vit_embeds = self.extract_feature(pixel_values)
         vit_embeds = vit_embeds[image_flags == 1]
+        vit_batch_size = pixel_values.shape[0]
 
         B, N, C = input_embeds.shape
         input_embeds = input_embeds.reshape(B * N, C)
 
+        if torch.distributed.get_rank() == 0:
+            print(f'dynamic ViT batch size: {vit_batch_size}, images per sample: {vit_batch_size / B}, dynamic token length: {N}')
+
         input_ids = input_ids.reshape(B * N)
         selected = (input_ids == self.img_context_token_id)
         try:
             input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds.reshape(-1, C)
-        except:
-            pass
+        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.model(
+        outputs = self.language_model(
             inputs_embeds=input_embeds,
             attention_mask=attention_mask,
             position_ids=position_ids,
@@ -313,8 +129,7 @@ class InternVLChatModel(PreTrainedModel):
             output_hidden_states=output_hidden_states,
             return_dict=return_dict,
         )
-        hidden_states = outputs[0]
-        logits = self.language_model.lm_head(hidden_states)
+        logits = outputs.logits
 
         loss = None
         if labels is not None:
@@ -350,6 +165,11 @@ class InternVLChatModel(PreTrainedModel):
         # 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):
@@ -364,41 +184,100 @@ class InternVLChatModel(PreTrainedModel):
                 output_hidden_states=True,
                 return_dict=True).hidden_states[self.select_layer]
         vit_embeds = vit_embeds[:, 1:, :]
-        # if torch.distributed.get_rank() == 0:
-        #     print("before pixel shuffle:", vit_embeds.shape)
+
         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])
-        # if torch.distributed.get_rank() == 0:
-        #     print("after pixel shuffle:", vit_embeds.shape)
         vit_embeds = self.mlp1(vit_embeds)
         return vit_embeds
 
-    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
-             IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>'):
+    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
 
-        from .conversation import get_conv_template
+        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.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'].cuda()
+        attention_mask = model_inputs['attention_mask'].cuda()
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+        generation_config['eos_token_id'] = eos_token_id
+        generation_output = self.generate(
+            pixel_values=pixel_values,
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **generation_config
+        )
+        responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
+        responses = [response.split(template.sep)[0].strip() for response in responses]
+        return responses
+
+    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
+             num_patches_list=None, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>',
+             verbose=False):
+
+        if history is None and pixel_values is not None and '<image>' not in question:
+            question = '<image>\n' + question
+
+        if num_patches_list is None:
+            num_patches_list = [pixel_values.shape[0]] if pixel_values is not None else []
+        assert pixel_values is None or len(pixel_values) == sum(num_patches_list)
+
+        img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
+        self.img_context_token_id = img_context_token_id
 
         template = get_conv_template(self.template)
-        if history is None:
-            history = []
-            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token + IMG_END_TOKEN
-            question = image_tokens + '\n' + question
-        else:
-            for (old_question, old_answer) in history:
-                template.append_message(template.roles[0], old_question)
-                template.append_message(template.roles[1], old_answer)
+        template.system_message = self.system_message
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
+
+        history = [] if history is None else history
+        for (old_question, old_answer) in history:
+            template.append_message(template.roles[0], old_question)
+            template.append_message(template.roles[1], old_answer)
         template.append_message(template.roles[0], question)
         template.append_message(template.roles[1], None)
         query = template.get_prompt()
+
+        if verbose and pixel_values is not None:
+            image_bs = pixel_values.shape[0]
+            print(f'dynamic ViT batch size: {image_bs}')
+
+        for num_patches in num_patches_list:
+            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
+            query = query.replace('<image>', image_tokens, 1)
+
         model_inputs = tokenizer(query, return_tensors='pt')
         input_ids = model_inputs['input_ids'].cuda()
         attention_mask = model_inputs['attention_mask'].cuda()
-
+        generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,
             input_ids=input_ids,
@@ -406,10 +285,15 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
+        response = response.split(template.sep)[0].strip()
         history.append((question, response))
         if return_history:
             return response, history
         else:
+            query_to_print = query.replace(IMG_CONTEXT_TOKEN, '')
+            query_to_print = query_to_print.replace(f'{IMG_START_TOKEN}{IMG_END_TOKEN}', '<image>')
+            if verbose:
+                print(query_to_print, response)
             return response
 
     @torch.no_grad()
@@ -431,7 +315,6 @@ class InternVLChatModel(PreTrainedModel):
                 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)

runs/Feb18_13-14-12_SH-IDC1-10-140-37-8/index.html

@@ -0,0 +1,15 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
+<html>
+<head>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+<title>Directory listing for /InternVL-Chat-V1-2-Plus/runs/Feb18_13-14-12_SH-IDC1-10-140-37-8/</title>
+</head>
+<body>
+<h1>Directory listing for /InternVL-Chat-V1-2-Plus/runs/Feb18_13-14-12_SH-IDC1-10-140-37-8/</h1>
+<hr>
+<ul>
+<li><a href="events.out.tfevents.1708234550.SH-IDC1-10-140-37-8.124298.0">events.out.tfevents.1708234550.SH-IDC1-10-140-37-8.124298.0</a></li>
+</ul>
+<hr>
+</body>
+</html>

runs/Feb18_14-05-57_SH-IDC1-10-140-37-8/index.html

@@ -0,0 +1,15 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
+<html>
+<head>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+<title>Directory listing for /InternVL-Chat-V1-2-Plus/runs/Feb18_14-05-57_SH-IDC1-10-140-37-8/</title>
+</head>
+<body>
+<h1>Directory listing for /InternVL-Chat-V1-2-Plus/runs/Feb18_14-05-57_SH-IDC1-10-140-37-8/</h1>
+<hr>
+<ul>
+<li><a href="events.out.tfevents.1708237619.SH-IDC1-10-140-37-8.185381.0">events.out.tfevents.1708237619.SH-IDC1-10-140-37-8.185381.0</a></li>
+</ul>
+<hr>
+</body>
+</html>

runs/index.html

@@ -0,0 +1,16 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
+<html>
+<head>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+<title>Directory listing for /InternVL-Chat-V1-2-Plus/runs/</title>
+</head>
+<body>
+<h1>Directory listing for /InternVL-Chat-V1-2-Plus/runs/</h1>
+<hr>
+<ul>
+<li><a href="Feb18_13-14-12_SH-IDC1-10-140-37-8/">Feb18_13-14-12_SH-IDC1-10-140-37-8/</a></li>
+<li><a href="Feb18_14-05-57_SH-IDC1-10-140-37-8/">Feb18_14-05-57_SH-IDC1-10-140-37-8/</a></li>
+</ul>
+<hr>
+</body>
+</html>

tokenizer_config.json

@@ -131,7 +131,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "legacy": true,
-  "model_max_length": 1280,
+  "model_max_length": 4096,
   "pad_token": "<unk>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,