README.md~

---
license: other
pipeline_tag: text-generation
---


<p align="center">
    <img src="logo_en.png" width="400"/>
<p>

<p align="center">
    <b><font size="6">InternLM-XComposer2</font></b> 
<p>

<div align="center">

[💻Github Repo](https://github.com/InternLM/InternLM-XComposer)

[Paper](https://arxiv.org/abs/2401.16420)

</div>

**InternLM-XComposer2** is a vision-language large model (VLLM) based on [InternLM2](https://github.com/InternLM/InternLM) for advanced text-image comprehension and composition. 

We release InternLM-XComposer2 series in two versions:

- InternLM-XComposer2-VL: The pretrained VLLM model with InternLM2 as the initialization of the LLM, achieving strong performance on various multimodal benchmarks.
- InternLM-XComposer2: The finetuned VLLM for *Free-from Interleaved Text-Image Composition*.

This is the 4-bit version of InternLM-XComposer2-VL

## Quickstart
We provide a simple example to show how to use InternLM-XComposer with 🤗 Transformers.
```python
import torch, auto_gptq
from transformers import AutoModel, AutoTokenizer 
from auto_gptq.modeling import BaseGPTQForCausalLM

auto_gptq.modeling._base.SUPPORTED_MODELS = ["internlm"]
torch.set_grad_enabled(False)

class InternLMXComposer2QForCausalLM(BaseGPTQForCausalLM):
    layers_block_name = "model.layers"
    outside_layer_modules = [
        'vit', 'vision_proj', 'model.tok_embeddings', 'model.norm', 'output', 
    ]
    inside_layer_modules = [
        ["attention.wqkv.linear"],
        ["attention.wo.linear"],
        ["feed_forward.w1.linear", "feed_forward.w3.linear"],
        ["feed_forward.w2.linear"],
    ]
 
# init model and tokenizer
model = InternLMXComposer2QForCausalLM.from_quantized(
  'internlm/internlm-xcomposer2-vl-7b-4bit', trust_remote_code=True, device="cuda:0").eval()
tokenizer = AutoTokenizer.from_pretrained(
  'internlm/internlm-xcomposer2-vl-7b-4bit', trust_remote_code=True)

text = '<ImageHere>Please describe this image in detail.'
image = 'examples/image1.webp'
with torch.cuda.amp.autocast(): 
  response, _ = model.chat(tokenizer, query=query, image=image, history=[], do_sample=False) 
print(response)
#The image features a quote by Oscar Wilde, "Live life with no excuses, travel with no regrets." 
#The quote is displayed in white text against a dark background. In the foreground, there are two silhouettes of people standing on a hill at sunset. 
#They appear to be hiking or climbing, as one of them is holding a walking stick. 
#The sky behind them is painted with hues of orange and purple, creating a beautiful contrast with the dark figures.

```

### Import from Transformers
To load the InternLM-XComposer2-VL-7B model using Transformers, use the following code:
```python
import torch
from PIL import image
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2-vl-7b"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()
```

### 通过 Transformers 加载
通过以下的代码加载 InternLM-XComposer2-VL-7B 模型

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
ckpt_path = "internlm/internlm-xcomposer2-vl-7b"
tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True).cuda()
# `torch_dtype=torch.float16` 可以令模型以 float16 精度加载，否则 transformers 会将模型加载为 float32，导致显存不足
model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()
```

### Open Source License
The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow free commercial usage. To apply for a commercial license, please fill in the application form (English)/申请表（中文）. For other questions or collaborations, please contact [email protected].