README.md

@@ -1,5 +1,5 @@
 ---
-title: TheBloek/WizardCoder-15B-1.0-GGML
+title: TheBloke/WizardCoder-15B-1.0-GGML
 emoji: 🚀
 colorFrom: green
 colorTo: green

app.py

@@ -1,13 +1,13 @@
-"""Run codes"""
+"""Run codes."""
 # pylint: disable=line-too-long, broad-exception-caught, invalid-name, missing-function-docstring, too-many-instance-attributes, missing-class-docstring
 # import gradio
 
 # gradio.load("models/WizardLM/WizardCoder-15B-V1.0").launch()
 
 import os
-from pathlib import Path
 import time
 from dataclasses import asdict, dataclass
+from pathlib import Path
 from types import SimpleNamespace
 
 import gradio as gr
@@ -164,7 +164,7 @@ def generate(
     system_prompt: str = default_system_prompt,
     user_prompt: str = "",
 ):
-    """Run model inference, will return a Generator if streaming is true"""
+    """Run model inference, will return a Generator if streaming is true."""
     # if not user_prompt.strip():
     return llm(
         format_prompt(
@@ -211,7 +211,7 @@ logger.info("done dl")
 _ = """
 llm = AutoModelForCausalLM.from_pretrained(
     "TheBloke/WizardCoder-15B-1.0-GGML",
-    model_file="",
+    model_file="WizardCoder-15B-1.0.ggmlv3.q4_0.bin",
     model_type="starcoder",
     threads=8
 )
@@ -222,16 +222,16 @@ logger.debug(f"{os.cpu_count()=}")
 if "WizardCoder" in MODEL_FILENAME:
     _ = Path("models", MODEL_FILENAME).absolute().as_posix()
     LLM = AutoModelForCausalLM.from_pretrained(
-        "TheBloke/WizardCoder-15B-1.0-GGML",
+        REPO_ID,
         model_file=_,
         model_type="starcoder",
         threads=os.cpu_count() // 2,  # type: ignore
     )
 # LLM = AutoModelForCausalLM.from_pretrained(
-    # "TheBloke/WizardCoder-15B-1.0-GGML",
-    # model_file=MODEL_FILENAME,
-    # model_type="starcoder",
-    # threads=os.cpu_count() // 2  # type: ignore
+# "TheBloke/WizardCoder-15B-1.0-GGML",
+# model_file=MODEL_FILENAME,
+# model_type="starcoder",
+# threads=os.cpu_count() // 2  # type: ignore
 # )
 
 cpu_count = os.cpu_count() // 2  # type: ignore