Descargando y probando el modelo

.gitignore

@@ -0,0 +1,5 @@
+.gradio
+bot
+chat_bot_test.py
+main.py
+model

app.py

@@ -0,0 +1,44 @@
+import langchain_community,langchain
+from langchain_community.llms import LlamaCpp
+from langchain.schema import AIMessage, HumanMessage, SystemMessage
+import gradio as gr
+
+# Define the model path
+model_path = "./model/Model-1.2B-Q8_0.gguf"
+system_message = "You are a helpful assistant who acts like a pirate."
+llm = LlamaCpp(
+    model_path=model_path,
+    temperature=0.8,
+    max_tokens=250,
+    top_p=0.6,    
+    verbose=True
+)
+
+def stream_response(message, history):
+    print(f"Input: {message}. History: {history}\n")
+
+    history_langchain_format = []
+    history_langchain_format.append(SystemMessage(content=system_message))
+
+    for human, ai in history:
+        history_langchain_format.append(HumanMessage(content=human))
+        history_langchain_format.append(AIMessage(content=ai))
+
+    if message is not None:
+        history_langchain_format.append(HumanMessage(content=message))
+        partial_message = ""
+        for response in llm.stream(history_langchain_format):   
+            partial_message += response
+            yield partial_message
+
+
+demo_interface = gr.ChatInterface(
+
+    stream_response,
+    textbox=gr.Textbox(placeholder="Send to the LLM...",
+                       container=False,
+                       autoscroll=True,
+                       scale=7),
+)
+
+demo_interface.launch(share=False, debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+langchain-community==0.3.8
+langchain==0.3.8
+llama_cpp_python==0.3.2