Update README.md

README.md

@@ -1,73 +1,73 @@
----
-license: apache-2.0
-language:
-- en
-library_name: transformers
-pipeline_tag: image-text-to-text
-tags:
-- multimodal
-- aria
----
-<!-- <p align="center">
-  <br>Aria</br>
-</p>  -->
-
-This is a fork of the [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) model. The only modification is replacing [grouped GEMM](https://github.com/tgale96/grouped_gemm) with a sequential MLP. In this configuration, each expert is implemented as a `torch.nn.Linear` layer executed in sequence. This adjustment simplifies quantization with current open-source libraries, which are optimized for `nn.Linear` layers. 
-
-While the sequential MLP approach aids in easier quantization, using grouped GEMM provides the advantage of faster inference speed.
-
-
-## Quick Start
-### Installation
-```
-pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
-pip install flash-attn --no-build-isolation
-```
-
-### Inference
-
-```python
-import requests
-import torch
-from PIL import Image
-from transformers import AutoModelForCausalLM, AutoProcessor
-
-model_id_or_path = "rhymes-ai/Aria-sequential_mlp"
-
-model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
-
-processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
-
-image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
-
-image = Image.open(requests.get(image_path, stream=True).raw)
-
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {"text": None, "type": "image"},
-            {"text": "what is the image?", "type": "text"},
-        ],
-    }
-]
-
-text = processor.apply_chat_template(messages, add_generation_prompt=True)
-inputs = processor(text=text, images=image, return_tensors="pt")
-inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
-inputs = {k: v.to(model.device) for k, v in inputs.items()}
-
-with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
-    output = model.generate(
-        **inputs,
-        max_new_tokens=500,
-        stop_strings=["<|im_end|>"],
-        tokenizer=processor.tokenizer,
-        do_sample=True,
-        temperature=0.9,
-    )
-    output_ids = output[0][inputs["input_ids"].shape[1]:]
-    result = processor.decode(output_ids, skip_special_tokens=True)
-
-print(result)
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- aria
+---
+<!-- <p align="center">
+  <br>Aria</br>
+</p>  -->
+
+This is a fork of the [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) model. The only modification is replacing [grouped GEMM](https://github.com/tgale96/grouped_gemm) with a sequential MLP. In this configuration, each expert is implemented as a `torch.nn.Linear` layer executed in sequence. This adjustment simplifies quantization with current open-source libraries, which are optimized for `nn.Linear` layers. 
+
+While the sequential MLP approach aids in easier quantization, using grouped GEMM provides the advantage of faster training speed.
+
+
+## Quick Start
+### Installation
+```
+pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
+pip install flash-attn --no-build-isolation
+```
+
+### Inference
+
+```python
+import requests
+import torch
+from PIL import Image
+from transformers import AutoModelForCausalLM, AutoProcessor
+
+model_id_or_path = "rhymes-ai/Aria-sequential_mlp"
+
+model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
+
+processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
+
+image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
+
+image = Image.open(requests.get(image_path, stream=True).raw)
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"text": None, "type": "image"},
+            {"text": "what is the image?", "type": "text"},
+        ],
+    }
+]
+
+text = processor.apply_chat_template(messages, add_generation_prompt=True)
+inputs = processor(text=text, images=image, return_tensors="pt")
+inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
+inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
+    output = model.generate(
+        **inputs,
+        max_new_tokens=500,
+        stop_strings=["<|im_end|>"],
+        tokenizer=processor.tokenizer,
+        do_sample=True,
+        temperature=0.9,
+    )
+    output_ids = output[0][inputs["input_ids"].shape[1]:]
+    result = processor.decode(output_ids, skip_special_tokens=True)
+
+print(result)
 ```