Update app.py

app.py

@@ -1,25 +1,32 @@
-#Python版本的transformers pipeline API
-#https://huggingface.co/docs/transformers/main_classes/pipelines
-
-#Java版本的transformers pipeline API
-#https://huggingface.co/docs/transformers.js/pipelines#available-tasks
-
-#Python版本示例：https://huggingface.co/docs/transformers/main_classes/pipelines
-from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
-
-# Sentiment analysis pipeline
-analyzer = pipeline("sentiment-analysis")
-#sentiment-analysis的default model是distilbert-base-uncased-finetuned-sst-2-english
-#https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english?text=I+like+you.+I+love+you
-#https://huggingface.co/blog/sentiment-analysis-python
-
-# Question answering pipeline, specifying the checkpoint identifier
-oracle = pipeline(
-    "question-answering", model="distilbert-base-cased-distilled-squad", tokenizer="bert-base-cased"
-)
-
-# Named entity recognition pipeline, passing in a specific model and tokenizer
-model = AutoModelForTokenClassification.from_pretrained("dbmdz/bert-large-cased-finetuned-conll03-english")
-tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
-recognizer = pipeline("ner", model=model, tokenizer=tokenizer)
+#https://huggingface.co/TheBloke/starchat-beta-GPTQ
+
+from transformers import AutoTokenizer, pipeline, logging
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+import argparse
+
+model_name_or_path = "TheBloke/starchat-beta-GPTQ"
+# Or to load it locally, pass the local download path
+# model_name_or_path = "/path/to/models/The_Bloke_starchat-beta-GPTQ"
+
+use_triton = False
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
+        use_safetensors=True,
+        #device="cuda:0",
+        use_triton=use_triton,
+        quantize_config=None)
+
+# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
+logging.set_verbosity(logging.CRITICAL)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+prompt_template = "<|system|>\n<|end|>\n<|user|>\n{query}<|end|>\n<|assistant|>"
+prompt = prompt_template.format(query="How do I sort a list in Python?")
+# We use a special <|end|> token with ID 49155 to denote ends of a turn
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2, top_k=50, top_p=0.95, eos_token_id=49155)
+# You can sort a list in Python by using the sort() method. Here's an example:\n\n```\nnumbers = [3, 1, 4, 1, 5, 9, 2, 6, 5, 3, 5]\nnumbers.sort()\nprint(numbers)\n```\n\nThis will sort the list in place and print the sorted list.
+print(outputs[0]['generated_text'])