Update README.md (#1)

- Update README.md (7b8d7c66db60c1ab6e9dc94b34574f15e0340b16)


Co-authored-by: Gen Luo <[email protected]>

README.md

@@ -88,95 +88,6 @@ We provide an example code to run Mono-InternVL-2B using `transformers`.
 
 > Please use transformers==4.37.2TODO to ensure the model works normally.
 
-### Model Loading
-
-#### 16-bit (bf16 / fp16)
-
-```python
-import torch
-from transformers import AutoTokenizer, AutoModel
-path = "OpenGVLab/Mono-InternVL-2B"
-model = AutoModel.from_pretrained(
-    path,
-    torch_dtype=torch.bfloat16,
-    low_cpu_mem_usage=True,
-    use_flash_attn=True,
-    trust_remote_code=True).eval().cuda()
-```
-
-#### BNB 8-bit Quantization
-
-```python
-import torch
-from transformers import AutoTokenizer, AutoModel
-path = "OpenGVLab/Mono-InternVL-2B"
-model = AutoModel.from_pretrained(
-    path,
-    torch_dtype=torch.bfloat16,
-    load_in_8bit=True,
-    low_cpu_mem_usage=True,
-    use_flash_attn=True,
-    trust_remote_code=True).eval()
-```
-
-#### BNB 4-bit Quantization
-
-```python
-import torch
-from transformers import AutoTokenizer, AutoModel
-path = "OpenGVLab/Mono-InternVL-2B"
-model = AutoModel.from_pretrained(
-    path,
-    torch_dtype=torch.bfloat16,
-    load_in_4bit=True,
-    low_cpu_mem_usage=True,
-    use_flash_attn=True,
-    trust_remote_code=True).eval()
-```
-
-#### 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 = {'Mono-InternVL-2B': 24}[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/Mono-InternVL-2B"
-device_map = split_model('Mono-InternVL-2B')
-model = AutoModel.from_pretrained(
-    path,
-    torch_dtype=torch.bfloat16,
-    low_cpu_mem_usage=True,
-    use_flash_attn=True,
-    trust_remote_code=True,
-    device_map=device_map).eval()
-```
 
 ### Inference with Transformers
 
@@ -300,267 +211,6 @@ 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(f'User: {question}\nAssistant: {response}')
 
-# multi-image multi-round conversation, combined images (多图多轮对话，拼接图像)
-pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
-pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
-pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
-
-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}\nAssistant: {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}\nAssistant: {response}')
-
-# multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
-pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
-pixel_values2 = load_image('./examples/image2.jpg', max_num=12).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)]
-
-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}\nAssistant: {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}\nAssistant: {response}')
-
-# batch inference, single image per sample (单图批处理)
-pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
-pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
-num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
-pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
-
-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}\nAssistant: {response}')
-
-# video multi-round conversation (视频多轮对话)
-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, input_size=448, max_num=1, 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 = [], []
-    transform = build_transform(input_size=input_size)
-    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')
-        img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num)
-        pixel_values = [transform(tile) for tile in img]
-        pixel_values = torch.stack(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
-
-video_path = './examples/red-panda.mp4'
-pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1)
-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}\nAssistant: {response}')
-
-question = 'Describe this video in detail. Don\'t repeat.'
-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}\nAssistant: {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
-```
-
-## Finetune
-
-Many repositories now support fine-tuning of the InternVL series models, including [InternVL](https://github.com/OpenGVLab/InternVL), [SWIFT](https://github.com/modelscope/ms-swift), [XTurner](https://github.com/InternLM/xtuner), and others. Please refer to their documentation for more details on fine-tuning.
-
-## Deployment
-
-### LMDeploy
-
-LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by the MMRazor and MMDeploy teams.
-
-```sh
-pip install lmdeploy==0.5.3
-```
-
-LMDeploy abstracts the complex inference process of multi-modal Vision-Language Models (VLM) into an easy-to-use pipeline, similar to the Large Language Model (LLM) inference pipeline.
-
-#### A 'Hello, world' example
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig
-from lmdeploy.vl import load_image
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-response = pipe(('describe this image', image))
-print(response.text)
-```
-
-If `ImportError` occurs while executing this case, please install the required dependency packages as prompted.
-
-#### Multi-images inference
-
-When dealing with multiple images, you can put them all in one list. Keep in mind that multiple images will lead to a higher number of input tokens, and as a result, the size of the context window typically needs to be increased.
-
-> Warning: Due to the scarcity of multi-image conversation data, the performance on multi-image tasks may be unstable, and it may require multiple attempts to achieve satisfactory results.
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig
-from lmdeploy.vl import load_image
-from lmdeploy.vl.constants import IMAGE_TOKEN
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-
-image_urls=[
-    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
-    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg'
-]
-
-images = [load_image(img_url) for img_url in image_urls]
-# Numbering images improves multi-image conversations
-response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images))
-print(response.text)
-```
-
-#### Batch prompts inference
-
-Conducting inference with batch prompts is quite straightforward; just place them within a list structure:
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig
-from lmdeploy.vl import load_image
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-
-image_urls=[
-    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
-    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg"
-]
-prompts = [('describe this image', load_image(img_url)) for img_url in image_urls]
-response = pipe(prompts)
-print(response)
-```
-
-#### Multi-turn conversation
-
-There are two ways to do the multi-turn conversations with the pipeline. One is to construct messages according to the format of OpenAI and use above introduced method, the other is to use the `pipeline.chat` interface.
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
-from lmdeploy.vl import load_image
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-
-image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
-gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
-sess = pipe.chat(('describe this image', image), gen_config=gen_config)
-print(sess.response.text)
-sess = pipe.chat('What is the woman doing?', session=sess, gen_config=gen_config)
-print(sess.response.text)
-```
-
-#### Service
-
-LMDeploy's `api_server` enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup:
-
-```shell
-lmdeploy serve api_server OpenGVLab/Mono-InternVL-2B --backend turbomind --server-port 23333
-```
-
-To use the OpenAI-style interface, you need to install OpenAI:
-
-```shell
-pip install openai
-```
-
-Then, use the code below to make the API call:
-
-```python
-from openai import OpenAI
-
-client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
-model_name = client.models.list().data[0].id
-response = client.chat.completions.create(
-    model=model_name,
-    messages=[{
-        'role':
-        'user',
-        'content': [{
-            'type': 'text',
-            'text': 'describe this image',
-        }, {
-            'type': 'image_url',
-            'image_url': {
-                'url':
-                'https://modelscope.oss-cn-beijing.aliyuncs.com/resource/tiger.jpeg',
-            },
-        }],
-    }],
-    temperature=0.8,
-    top_p=0.8)
-print(response)
-```
 
 ## License
 
@@ -634,140 +284,6 @@ Mono-InternVL在性能上优于当前最先进的MLLM Mini-InternVL-2B-1.5，并
 
 示例代码请[点击这里](#quick-start)。
 
-## 微调
-
-许多仓库现在都支持 InternVL 系列模型的微调，包括 [InternVL](https://github.com/OpenGVLab/InternVL)、[SWIFT](https://github.com/modelscope/ms-swift)、[XTurner](https://github.com/InternLM/xtuner) 等。请参阅它们的文档以获取更多微调细节。
-
-## 部署
-
-### LMDeploy
-
-LMDeploy 是由 MMRazor 和 MMDeploy 团队开发的用于压缩、部署和服务大语言模型（LLM）的工具包。
-
-```sh
-pip install lmdeploy==0.5.3
-```
-
-LMDeploy 将多模态视觉-语言模型（VLM）的复杂推理过程抽象为一个易于使用的管道，类似于大语言模型（LLM）的推理管道。
-
-#### 一个“你好，世界”示例
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig
-from lmdeploy.vl import load_image
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-response = pipe(('describe this image', image))
-print(response.text)
-```
-
-如果在执行此示例时出现 `ImportError`，请按照提示安装所需的依赖包。
-
-#### 多图像推理
-
-在处理多张图像时，可以将它们全部放入一个列表中。请注意，多张图像会导致输入 token 数量增加，因此通常需要增加上下文窗口的大小。
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig
-from lmdeploy.vl import load_image
-from lmdeploy.vl.constants import IMAGE_TOKEN
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-
-image_urls=[
-    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
-    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg'
-]
-
-images = [load_image(img_url) for img_url in image_urls]
-# Numbering images improves multi-image conversations
-response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images))
-print(response.text)
-```
-
-#### 批量Prompt推理
-
-使用批量Prompt进行推理非常简单；只需将它们放在一个列表结构中：
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig
-from lmdeploy.vl import load_image
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-
-image_urls=[
-    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
-    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg"
-]
-prompts = [('describe this image', load_image(img_url)) for img_url in image_urls]
-response = pipe(prompts)
-print(response)
-```
-
-#### 多轮对话
-
-使用管道进行多轮对话有两种方法。一种是根据 OpenAI 的格式构建消息并使用上述方法，另一种是使用 `pipeline.chat` 接口。
-
-```python
-from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
-from lmdeploy.vl import load_image
-
-model = 'OpenGVLab/Mono-InternVL-2B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
-
-image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
-gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
-sess = pipe.chat(('describe this image', image), gen_config=gen_config)
-print(sess.response.text)
-sess = pipe.chat('What is the woman doing?', session=sess, gen_config=gen_config)
-print(sess.response.text)
-```
-
-#### API部署
-
-LMDeploy 的 `api_server` 使模型能够通过一个命令轻松打包成服务。提供的 RESTful API 与 OpenAI 的接口兼容。以下是服务启动的示例：
-
-```shell
-lmdeploy serve api_server OpenGVLab/Mono-InternVL-2B --backend turbomind --server-port 23333
-```
-
-为了使用OpenAI风格的API接口，您需要安装OpenAI:
-
-```shell
-pip install openai
-```
-
-然后，使用下面的代码进行API调用:
-
-```python
-from openai import OpenAI
-
-client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
-model_name = client.models.list().data[0].id
-response = client.chat.completions.create(
-    model=model_name,
-    messages=[{
-        'role':
-        'user',
-        'content': [{
-            'type': 'text',
-            'text': 'describe this image',
-        }, {
-            'type': 'image_url',
-            'image_url': {
-                'url':
-                'https://modelscope.oss-cn-beijing.aliyuncs.com/resource/tiger.jpeg',
-            },
-        }],
-    }],
-    temperature=0.8,
-    top_p=0.8)
-print(response)
-```
 
 ## 开源许可证