Create app.py

app.py

@@ -0,0 +1,22 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "qvac/genesisI-model"
+
+tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,  # or torch.float16 on T4
+    device_map="auto"
+)
+
+prompt = "Explain precision vs. recall in one paragraph."
+inputs = tok(prompt, return_tensors="pt").to(model.device)
+out = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    do_sample=True,
+    top_p=0.9,
+    temperature=0.7,
+)
+print(tok.decode(out[0], skip_special_tokens=True))