Update README.md

README.md

@@ -3,15 +3,7 @@ license: apache-2.0
 pipeline_tag: image-text-to-text
 ---
 
-moondream2 is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)!
-
-**Benchmarks**
-
-| Release | VQAv2 | GQA | TextVQA | TallyQA (simple) | TallyQA (full) |
-| --- | --- | --- | --- | --- | --- |
-| 2024-03-04 | 74.2 | 58.5 | 36.4 | - | - |
-| 2024-03-06 | 75.4 | 59.8 | 43.1 | 79.5 | 73.2 |
-| **2024-03-13** (latest) | 76.8 | 60.6 | 46.4 | 79.6 | 73.3 |
+Fine tuned version of moondream2 for prompt generation from images. Moondream is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)!
 
 **Usage**
 
@@ -20,20 +12,25 @@ pip install transformers timm einops
 ```
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from PIL import Image
 
-model_id = "vikhyatk/moondream2"
-revision = "2024-03-06"
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, trust_remote_code=True, revision=revision
-)
-tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
+DEVICE = "cuda"
+DTYPE = torch.float32 if DEVICE == "cpu" else torch.float16 # CPU doesn't support float16
 
-image = Image.open('<IMAGE_PATH>')
-enc_image = model.encode_image(image)
-print(model.answer_question(enc_image, "Describe this image.", tokenizer))
-```
+tokenizer = AutoTokenizer.from_pretrained("gokaygokay/moondream-prompt")
+moondream = AutoModelForCausalLM.from_pretrained("gokaygokay/moondream-prompt",trust_remote_code=True,
+    torch_dtype=DTYPE, device_map={"": DEVICE})
+moondream.eval()
 
-The model is updated regularly, so we recommend pinning the model version to a
-specific release as shown above.
+image_path = "<image_path>"
+image = Image.open(image_path).convert("RGB")
+md_answer = moondream.answer_question(
+        moondream.encode_image(image),
+        "Describe this image and its style in a very detailed manner",
+        tokenizer=tokenizer,
+    )
+
+print(md_answer)
+```