gse brain engine: MiMo-V2.6 4-bit on ZeroGPU (free tier)

app.py

@@ -11,7 +11,7 @@ import torch
 import gradio as gr
 from transformers import (
     AutoModelForImageTextToText,
-    AutoProcessor,
+    AutoTokenizer,
     BitsAndBytesConfig,
 )
 
@@ -25,8 +25,8 @@ SYSTEM_PROMPT = (
     "(3) Output ONLY valid JSON when a JSON schema is requested."
 )
 
-print("Loading processor...", flush=True)
-processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
+print("Loading tokenizer...", flush=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
 
 print("Loading model in 4-bit...", flush=True)
 bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16)
@@ -51,9 +51,9 @@ def chat(message: str, history: list):
             messages.append({"role": "assistant", "content": h_asst})
         messages.append({"role": "user", "content": message})
 
-        text = processor.apply_chat_template(
+        text = tokenizer.apply_chat_template(
             messages, add_generation_prompt=True, tokenize=False)
-        inputs = processor(text=[text], return_tensors="pt").to("cuda")
+        inputs = tokenizer(text, return_tensors="pt").to("cuda")
         input_len = inputs["input_ids"].shape[1]
 
         with torch.inference_mode():
@@ -62,9 +62,9 @@ def chat(message: str, history: list):
                 max_new_tokens=1024,
                 temperature=0.2,
                 do_sample=True,
-                pad_token_id=processor.tokenizer.eos_token_id,
+                pad_token_id=tokenizer.eos_token_id,
             )
-        response = processor.batch_decode(
+        response = tokenizer.batch_decode(
             out[:, input_len:], skip_special_tokens=True)[0]
         return response.strip()
     except Exception as exc:  # never crash the Space; return the error loudly