initial commit

README.md

@@ -1,14 +1,8 @@
----
-title: Phi2 Personaforge Rag
-emoji: 👀
-colorFrom: gray
-colorTo: purple
-sdk: gradio
-sdk_version: 5.31.0
-app_file: app.py
-pinned: false
-license: mit
-short_description: phi2 model to test personaforge rag-end
----
+# Phi-2 NPC Chat (CPU)
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Simple inference demo for Microsoft Phi-2 model running on Hugging Face CPU Space.
+Useful for prototyping RAG/NPC logic.
+
+- Model: microsoft/phi-2
+- Interface: Gradio
+- Runtime: CPU (free tier)

app.py

@@ -0,0 +1,16 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+import gradio as gr
+
+model_id = "microsoft/phi-2"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def chat(prompt):
+    result = pipe(prompt, max_new_tokens=100, temperature=0.7)
+    return result[0]["generated_text"]
+
+iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Phi-2 NPC Chat")
+iface.launch()

requirements.txt

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