update

README.md

@@ -9,3 +9,49 @@ license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+curl -G "https://lseanlon-qwen25-api.hf.space/predict" \
+     --data-urlencode "image_url=https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg" \
+     --data-urlencode "prompt=Describe this image."
+
+
+      
+
+
+
+curl -G "https://lseanlon-qwen25-api.hf.space/" \
+     --data-urlencode "image_url=https://huggingface.co/front/assets/huggingface_logo-noborder.svg" \
+     --data-urlencode "prompt=Describe this image."
+
+
+curl -G "https://lseanlon-qwen25-api.hf.space/predict" \
+     --data-urlencode "image_url=https://images.all-free-download.com/images/thumbjpg/cat_hangover_relax_213869.jpg" \
+     --data-urlencode "prompt=Describe this image."
+
+ 
+
+curl -G "https://lseanlon-qwen25-api.hf.space/predict" \
+     --data-urlencode "prompt=why is the sky blue?"
+
+         
+
+
+FROM  qwen2.5-coder:7b
+PARAMETER num_ctx 48000
+
+ollama create -f ZModelfile qwen2.5:latest-custom
+
+curl http://localhost:11434/api/chat -d '{
+  "model": "qwen2.5:latest",
+  "messages": [
+    { "role": "user", "content": "why is the sky blue?" }
+  ]
+}'
+
+curl https://dry-taxes-fold.loca.lt/api/chat -d '{
+  "model": "qwen2.5:latest",
+  "messages": [
+    { "role": "user", "content": "why is the sky blue?" }
+  ]
+}'

main.py

@@ -46,3 +46,25 @@ def predict(image_url: str = Query(...), prompt: str = Query(...)):
         generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
     )
     return {"response": output_texts[0]}
+
+@app.get("/chat")
+def chat( prompt: str = Query(...)):
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant with vision abilities."},
+        {"role": "user", "content": [ {"type": "text", "text": prompt}]},
+    ]
+    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    video_inputs = process_vision_info(messages)
+    inputs = processor(
+        text=[text], 
+        videos=video_inputs,
+        padding=True,
+        return_tensors="pt",
+    ).to(model.device)
+    with torch.no_grad():
+        generated_ids = model.generate(**inputs, max_new_tokens=128)
+    generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
+    output_texts = processor.batch_decode(
+        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )
+    return {"response": output_texts[0]}