Update README.md

README.md

@@ -26,4 +26,69 @@ tvl was trained in bf16
 
 Train dataset contains:
  - GrandMaster-PRO-MAX dataset (60k samples)
- - Translated, humanized and merged by image subset of GQA (TODO)
+ - Translated, humanized and merged by image subset of GQA (TODO)
+
+## Bechmarks
+
+### TODO
+
+## Quickstart
+
+Your can simply run [this notebook](https://www.kaggle.com/code/artemdzhalilov/tvl-hand-test) or run code below.
+
+First install qwen-vl-utils and dev version of transformers:
+
+```bash
+pip install qwen-vl-utils
+pip install --no-cache-dir git+https://github.com/huggingface/transformers@19e6e80e10118f855137b90740936c0b11ac397f
+```
+
+And then run:
+
+```bash
+from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+import torch
+
+model = Qwen2VLForConditionalGeneration.from_pretrained(
+    "2Vasabi/tvl-mini-instruct-0.1", torch_dtype=torch.bfloat16, device_map="auto"
+)
+
+
+processor = AutoProcessor.from_pretrained("2Vasabi/tvl-mini-instruct-0.1")
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://i.ibb.co/d0QL8s6/images.jpg",
+            },
+            {"type": "text", "text": "Кратко опиши что ты видишь на изображении"},
+        ],
+    }
+]
+
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs = process_vision_info(messages)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+
+inputs = inputs.to("cuda")
+
+generated_ids = model.generate(**inputs, max_new_tokens=1000)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
+print(output_text)
+```