Update app.py

app.py

@@ -1,11 +1,16 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
+import requests
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+llm = Llama.from_pretrained(
+    repo_id="cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf",
+    filename="*Q4_K_S.gguf",
+    verbose=True,
+    n_ctx=32768,
+    n_threads=2,
+    chat_format="chatml"
+)
 
 def respond(
     message,
@@ -26,19 +31,19 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
+    response = llm.create_chat_completion(
+            messages=messages,
+            stream=True,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p
+        )
+    message_repl = ""
+    for chunk in response:
+        if len(chunk['choices'][0]["delta"]) != 0 and "content" in chunk['choices'][0]["delta"]:
+            message_repl = message_repl + \
+                chunk['choices'][0]["delta"]["content"]
+        yield message_repl
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """