them file

app.py

@@ -1,70 +1,12 @@
 # app.py
-import torch
 import gradio as gr
-from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
-
-# 1️⃣ Cấu hình và load model + tokenizer
-model_path = "vinai/PhoGPT-4B-Chat"
- 
-config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
-config.init_device = "cpu"
-
-model = AutoModelForCausalLM.from_pretrained("vinai/PhoGPT-4B-Chat", trust_remote_code=True)
-model.eval()
-tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
-
-
-def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
-    # 2.1 — Gom system message và history vào messages list
-    messages = [{"role": "system", "content": system_message}]
-    for u, b in history:
-        if u:
-            messages.append({"role": "user", "content": u})
-        if b:
-            messages.append({"role": "assistant", "content": b})
-    messages.append({"role": "user", "content": message})
-
-    # 2.2 — Tạo prompt chuẩn
-    input_prompt  = tokenizer.apply_chat_template(
-        messages,
-        tokenize=False,
-        add_generation_prompt=True
-    )
-
-    # 2.3 — Tokenize và đưa lên device
-    # inputs = tokenizer(input_prompt, return_tensors="pt")
-    input_ids = tokenizer(input_prompt, return_tensors="pt")  
-    # inputs = {k: v.to(model.device) for k, v in inputs.items()}
-
-    # 2.4 — Sinh text
-    outputs = model.generate(
-        inputs=input_ids["input_ids"], 
-        max_new_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
-        do_sample=True,
-        eos_token_id=tokenizer.eos_token_id,
-        pad_token_id=tokenizer.pad_token_id,
-    )
-    # print('!!!! OUTPUTS 1: ',outputs)
-    # 2.5 — Decode và tách phần assistant trả lời
-    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]  
-    print('!! OUTPUTS 2: ',response)
-
-    response = response.split("### Trả lời:")[1]
-    print('!!!! OUTPUTS 3: ',response)
-    return response
-
-    # 2.6 — Cập nhật history và trả về
-    # history.append((message, response))
-    # return history
-
-
+import phoGPT
 
+respond = phoGPT.respond()
 
 # 3️⃣ Giao diện Gradio
 demo = gr.ChatInterface(
-    respond,
+    respond, #câu phản hồi
     additional_inputs=[
         gr.Textbox("Bạn là một chatbot tiếng Việt thân thiện.", label="System message"),
         gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"),

git.txt

@@ -0,0 +1,4 @@
+git commit -am "Update space"; git push origin main
+
+git add test.py
+git rm test.py

phoGPT.py

@@ -0,0 +1,58 @@
+import torch
+from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
+
+# 1️⃣ Cấu hình và load model + tokenizer
+model_path = "vinai/PhoGPT-4B-Chat"
+ 
+config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
+config.init_device = "cpu"
+
+model = AutoModelForCausalLM.from_pretrained("vinai/PhoGPT-4B-Chat", trust_remote_code=True)
+model.eval()
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+
+
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
+    # 2.1 — Gom system message và history vào messages list
+    messages = [{"role": "system", "content": system_message}]
+    for u, b in history:
+        if u:
+            messages.append({"role": "user", "content": u})
+        if b:
+            messages.append({"role": "assistant", "content": b})
+    messages.append({"role": "user", "content": message})
+
+    # 2.2 — Tạo prompt chuẩn
+    input_prompt  = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+    # 2.3 — Tokenize và đưa lên device
+    # inputs = tokenizer(input_prompt, return_tensors="pt")
+    input_ids = tokenizer(input_prompt, return_tensors="pt")  
+    # inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+    # 2.4 — Sinh text
+    outputs = model.generate(
+        inputs=input_ids["input_ids"], 
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        do_sample=True,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.pad_token_id,
+    )
+    # print('!!!! OUTPUTS 1: ',outputs)
+    # 2.5 — Decode và tách phần assistant trả lời
+    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]  
+    print('!! OUTPUTS 2: ',response)
+
+    response = response.split("### Trả lời:")[1]
+    print('!!!! OUTPUTS 3: ',response)
+    return response
+
+    # 2.6 — Cập nhật history và trả về
+    # history.append((message, response))
+    # return history

test.py

@@ -0,0 +1,64 @@
+import gradio as gr # type: ignore
+from huggingface_hub import InferenceClient # type: ignore
+
+"""
+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")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    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
+
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()