first push

app.py

@@ -0,0 +1,26 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from PIL import Image
+import requests
+from io import BytesIO
+
+url = "https://d2h50zujfkj84t.cloudfront.net/product_images/Screenshot_2024-09-03_135657.png"
+response = requests.get(url)
+image = Image.open(BytesIO(response.content))
+
+
+model = AutoModelForCausalLM.from_pretrained(
+    "qresearch/llama-3.1-8B-vision-378",
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+).to("cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("qresearch/llama-3.1-8B-vision-378", use_fast=True,)
+
+print(
+    model.answer_question(
+        image, "Briefly describe the image", tokenizer, max_new_tokens=128, do_sample=True, temperature=0.3
+    ),
+)
+
+

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+pillow