Update README.md

README.md

@@ -3,6 +3,8 @@ license: apple-amlr
 license_name: apple-ascl
 license_link: https://github.com/apple/ml-fastvlm/blob/main/LICENSE_MODEL
 library_name: ml-fastvlm
+tags:
+- transformers
 ---
 # FastVLM: Efficient Vision Encoding for Vision Language Models
 
@@ -50,6 +52,58 @@ python predict.py --model-path /path/to/checkpoint-dir \
                   --image-file /path/to/image.png \
                   --prompt "Describe the image."
 ```
+### Run inference with Transformers (Remote Code)
+To run inference with transformers we can leverage `trust_remote_code` along with the following snippet:
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoTokenizer, AutoModelForCausalLM
+MID = "apple/FastVLM-7B"
+IMAGE_TOKEN_INDEX = -200  # what the model code looks for
+
+# Load
+tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MID,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto",
+    trust_remote_code=True,
+)
+
+# Build chat -> render to string (not tokens) so we can place <image> exactly
+messages = [
+    {"role": "user", "content": "<image>\nDescribe this image in detail."}
+]
+rendered = tok.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=False
+)
+pre, post = rendered.split("<image>", 1)
+
+# Tokenize the text *around* the image token (no extra specials!)
+pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
+post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids
+
+# Splice in the IMAGE token id (-200) at the placeholder position
+img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
+input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
+attention_mask = torch.ones_like(input_ids, device=model.device)
+
+# Preprocess image via the model's own processor
+img = Image.open("test-2.jpg").convert("RGB")
+px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
+px = px.to(model.device, dtype=model.dtype)
+
+# Generate
+with torch.no_grad():
+    out = model.generate(
+        inputs=input_ids,
+        attention_mask=attention_mask,
+        images=px,
+        max_new_tokens=128,
+    )
+print(tok.decode(out[0], skip_special_tokens=True))
+```
 
 
 ## Citation
@@ -62,4 +116,4 @@ If you found this model useful, please cite the following paper:
   month = {June},
   year = {2025},
 }
-```
+```