Update README.md

README.md

@@ -1,3 +1,72 @@
----
-license: gemma
----
+---
+license: gemma
+datasets:
+- BUAADreamer/llava-en-zh-2k
+language:
+- en
+- zh
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model: google/paligemma-3b-mix-448
+inference: false
+tags:
+- paligemma
+- llama-factory
+- mllm
+- vlm
+---
+
+# PaliGemma-3B-Chat-v0.1
+
+This model is fine-tuned from [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) using [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory).
+
+![examples](examples_en.png)
+
+## Usage
+
+```python
+import requests
+import torch
+from PIL import Image
+from transformers import AutoModelForVision2Seq, AutoProcessor, AutoTokenizer, TextStreamer
+
+
+model_id = "/raid/zhangrichong/data/zhengyw/llama_factory/models/paligemma-chat"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForVision2Seq.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+url = "hiyouga/PaliGemma-3B-Chat-v0.1"
+image = Image.open(requests.get(url, stream=True).raw)
+pixel_values = processor(images=[image], return_tensors="pt").to(model.device)["pixel_values"]
+
+messages = [
+    {"role": "user", "content": "What is in this image?"}
+]
+input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+image_token_id = tokenizer.convert_tokens_to_ids("<image>")
+image_prefix = torch.empty((1, getattr(processor, "image_seq_length")), dtype=input_ids.dtype).fill_(image_token_id)
+input_ids = torch.cat((image_prefix, input_ids), dim=-1).to(model.device)
+
+generate_ids = model.generate(input_ids, pixel_values=pixel_values, streamer=streamer, max_new_tokens=50)
+```
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.00001
+- num_train_epochs: 3.0
+- train_batch_size: 1
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- seed: 42
+- lr_scheduler_type: cosine
+- mixed_precision_training: bf16
+
+### Framework versions
+
+- Pytorch 2.3.0
+- Transformers 4.41.0