Added token counter

app.py

@@ -1,63 +1,53 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from tokenizers import Tokenizer
 
-"""
-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")
+llama3_tokenizer = Tokenizer.from_file("tokenizer-llama3.json")
+deepseek_coder_tokenizer = Tokenizer.from_file("tokenizer-deepseek-coder.json")
 
+def get_tokenizer(model):
+    tokenizer_mapping = {
+        "meta-llama/Meta-Llama-3-8B-Instruct": llama3_tokenizer, 
+        "deepseek-ai/deepseek-coder-7b-instruct-v1.5": deepseek_coder_tokenizer
+    }
+    if model not in tokenizer_mapping:
+        raise Exception(f"Model {model} not supported.")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    return tokenizer_mapping[model]
+
+def count_tokens(
+    model,
+    target_text,
 ):
-    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)",
+    print("###############################")
+    print(model)
+    tokenizer = get_tokenizer(model)
+    print(tokenizer)
+    toks = tokenizer.encode(target_text)
+    print(toks.ids)
+    yield len(toks.ids)
+   
+def greet(name, intensity):
+    return "Hello, " + name + "!" * int(intensity)
+
+demo = gr.Interface(
+    fn=count_tokens,
+    inputs=[
+        gr.Dropdown(
+            [
+                "meta-llama/Meta-Llama-3-8B-Instruct", 
+                "deepseek-ai/deepseek-coder-7b-instruct-v1.5", 
+            ], label="Model"
+        ),
+        gr.Textbox(
+            label="Input",
+            info="Text to count tokens for",
+            lines=10,
         ),
     ],
+    outputs=["text"],
 )
 
 
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+tokenizers==0.19.1
+gradio==4.40.0
+gradio_client==1.2.0