Upload 3 files

README.md

@@ -1,12 +1,12 @@
----
-title: DeepSeek-R1-Distill-Llama-8B
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 4.36.1
-app_file: app.py
-pinned: false
----
-
+---
+title: Chatbot Zero
+emoji: 💬
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 5.21.0
+app_file: app.py
+pinned: false
+---
+
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,140 +1,122 @@
-import gradio as gr
-import os
-import spaces
-from transformers import GemmaTokenizer, AutoModelForCausalLM
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-from threading import Thread
-
-# Set an environment variable
-HF_TOKEN = os.environ.get("HF_TOKEN", None)
-
-
-DESCRIPTION = '''
-<div>
-<h1 style="text-align: center;">deepseek-ai/DeepSeek-R1-Distill-Llama-8B</h1>
-</div>
-'''
-
-LICENSE = """
-<p/>
-
----
-"""
-
-PLACEHOLDER = """
-<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">DeepSeek-R1-Distill-Llama-8B</h1>
-   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
-</div>
-"""
-
-
-css = """
-h1 {
-  text-align: center;
-  display: block;
-}
-
-#duplicate-button {
-  margin: auto;
-  color: white;
-  background: #1565c0;
-  border-radius: 100vh;
-}
-"""
-
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-8B")
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-8B", device_map="auto")  # to("cuda:0") 
-terminators = [
-    tokenizer.eos_token_id,
-    tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
-
-@spaces.GPU(duration=120)
-def chat_llama3_8b(message: str, 
-              history: list, 
-              temperature: float, 
-              max_new_tokens: int
-             ) -> str:
-    """
-    Generate a streaming response using the llama3-8b model.
-    Args:
-        message (str): The input message.
-        history (list): The conversation history used by ChatInterface.
-        temperature (float): The temperature for generating the response.
-        max_new_tokens (int): The maximum number of new tokens to generate.
-    Returns:
-        str: The generated response.
-    """
-    conversation = []
-    for user, assistant in history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
-
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
-    
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-
-    generate_kwargs = dict(
-        input_ids= input_ids,
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        temperature=temperature,
-        eos_token_id=terminators,
-    )
-    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
-    if temperature == 0:
-        generate_kwargs['do_sample'] = False
-        
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        #print(outputs)
-        yield "".join(outputs)
-        
-
-# Gradio block
-chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
-
-with gr.Blocks(fill_height=True, css=css) as demo:
-    
-    gr.Markdown(DESCRIPTION)
-    gr.ChatInterface(
-        fn=chat_llama3_8b,
-        chatbot=chatbot,
-        fill_height=True,
-        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
-        additional_inputs=[
-            gr.Slider(minimum=0,
-                      maximum=1, 
-                      step=0.1,
-                      value=0.5, 
-                      label="Temperature", 
-                      render=False),
-            gr.Slider(minimum=128, 
-                      maximum=4096,
-                      step=1,
-                      value=1024, 
-                      label="Max new tokens", 
-                      render=False ),
-            ],
-        examples=[
-            ['How to setup a human base on Mars? Give short answer.'],
-            ['Explain theory of relativity to me like I’m 8 years old.'],
-            ['What is 9,000 * 9,000?'],
-            ['Write a pun-filled happy birthday message to my friend Alex.'],
-            ['Justify why a penguin might make a good king of the jungle.']
-            ],
-        cache_examples=False,
-                     )
-    
-    gr.Markdown(LICENSE)
-    
-if __name__ == "__main__":
-    demo.launch()
-    
+import spaces
+import gradio as gr
+import os
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig
+from threading import Thread
+import torch
+
+HF_TOKEN = os.getenv("HF_TOKEN", None)
+#REPO_ID = "deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
+REPO_ID = "nicoboss/DeepSeek-R1-Distill-Qwen-32B-Uncensored"
+
+DESCRIPTION = f'''
+<div>
+<h1 style="text-align: center;">{REPO_ID}</h1>
+</div>
+'''
+
+PLACEHOLDER = f"""
+<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">{REPO_ID}</h1>
+   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
+</div>
+"""
+
+css = """
+h1 {
+  text-align: center;
+  display: block;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}
+"""
+
+tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
+if torch.cuda.is_available():
+    nf4_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.bfloat16)
+    model = AutoModelForCausalLM.from_pretrained(REPO_ID, quantization_config=nf4_config)
+else: model = AutoModelForCausalLM.from_pretrained(REPO_ID, torch_dtype=torch.float32)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+@spaces.GPU(duration=59)
+def chat(message: str, 
+         history: list, 
+         temperature: float, 
+         max_new_tokens: int,
+         progress=gr.Progress(track_tqdm=True)
+        ):
+    try:
+        conversation = []
+        for user, assistant in history:
+            conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+        conversation.append({"role": "user", "content": message})
+
+        input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
+        
+        streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+
+        generate_kwargs = dict(
+            input_ids=input_ids,
+            streamer=streamer,
+            max_new_tokens=max_new_tokens,
+            do_sample=True,
+            temperature=temperature,
+            eos_token_id=terminators,
+        )
+        if temperature == 0: generate_kwargs['do_sample'] = False
+        
+        t = Thread(target=model.generate, kwargs=generate_kwargs)
+        t.start()
+
+        outputs = []
+        for text in streamer:
+            outputs.append(text)
+            yield "".join(outputs)
+    except Exception as e:
+        print(e)
+        gr.Warning(f"Error: {e}")
+        yield ""
+
+chatbot=gr.Chatbot(height=450, placeholder=PLACEHOLDER, label='Gradio ChatInterface')
+
+with gr.Blocks(fill_height=True, fill_width=True, css=css) as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.ChatInterface(
+        fn=chat,
+        chatbot=chatbot,
+        fill_height=True,
+        additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
+        additional_inputs=[
+            gr.Slider(minimum=0,
+                      maximum=1, 
+                      step=0.1,
+                      value=0.5, 
+                      label="Temperature", 
+                      render=False),
+            gr.Slider(minimum=128, 
+                      maximum=4096,
+                      step=1,
+                      value=1024, 
+                      label="Max new tokens", 
+                      render=False ),
+            ],
+        examples=[
+            ['How to setup a human base on Mars? Give short answer.'],
+            ['Explain theory of relativity to me like I’m 8 years old.'],
+            ['What is 9,000 * 9,000?'],
+            ['Write a pun-filled happy birthday message to my friend Alex.'],
+            ['Justify why a penguin might make a good king of the jungle.']
+            ],
+        cache_examples=False)
+
+if __name__ == "__main__":
+    demo.launch(ssr_mode=False)

requirements.txt

@@ -1,4 +1,5 @@
-huggingface_hub
-accelerate
-transformers
-SentencePiece
+huggingface_hub
+accelerate
+transformers
+sentencepiece
+bitsandbytes