switch back to 125M

app.py

@@ -2,7 +2,8 @@ import gradio as gr
 
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "flax-community/gpt-code-clippy-1.3B-apps-alldata-2"
+# model_name = "flax-community/gpt-code-clippy-1.3B-apps-alldata"
+model_name = "flax-community/gpt-code-clippy-125M-apps-alldata"
 model = AutoModelForCausalLM.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 tokenizer.pad_token = tokenizer.eos_token
@@ -39,14 +40,14 @@ def generate_solution(question, starter_code="", temperature=1., num_beams=1):
         top_p=0.95,
         pad_token_id=tokenizer.pad_token_id,
         early_stopping=True,
-        temperature=1.,
+        temperature=temperature,
         num_beams=int(num_beams),
         no_repeat_ngram_size=None,
         repetition_penalty=None,
         num_return_sequences=None,
     )
     
-    return format_outputs(tokenizer.decode(output[0][start:]).strip())
+    return format_outputs(tokenizer.decode(output[0][start:], skip_special_tokens=True).strip())
 
 
 _EXAMPLES = [