first try

pyproject.toml

@@ -0,0 +1,16 @@
+[tool.poetry]
+name = "visado"
+version = "0.1.0"
+description = ""
+authors = ["mateuor2d2 <mateuor2d2@gmail.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+torch = "^2.5.0"
+transformers = "^4.45.2"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

test.py

@@ -0,0 +1,31 @@
+from handler import EndpointHandler
+
+# init handler
+my_handler = EndpointHandler(path=".")
+# prepare sample payload
+text = """We introduce Mistral 7B, a 7–billion-parameter language model engineered for
+superior performance and efficiency. Mistral 7B outperforms the best open 13B
+model (Llama 2) across all evaluated benchmarks, and the best released 34B
+model (Llama 1) in reasoning, mathematics, and code generation. Our model
+leverages grouped-query attention (GQA) for faster inference, coupled with sliding
+window attention (SWA) to effectively handle sequences of arbitrary length with a
+reduced inference cost. We also provide a model fine-tuned to follow instructions,
+Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and
+automated benchmarks. Our models are released under the Apache 2.0 license.
+Code: <https://github.com/mistralai/mistral-src>
+Webpage: <https://mistral.ai/news/announcing-mistral-7b/>"""
+
+template = """{
+    "Model": {
+        "Name": "",
+        "Number of parameters": "",
+        "Number of max token": "",
+        "Architecture": []
+    },
+    "Usage": {
+        "Use case": [],
+        "Licence": ""
+    }
+}"""
+resultado=my_handler({"inputs": {"text": text, "template": template}})
+print(resultado)