changing model as a test

app.py

@@ -28,12 +28,13 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=350, chunk_overlap=10)
-# model_id = HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta", model_kwargs={"temperature":0.1, "max_new_tokens":300})
+# text_splitter = RecursiveCharacterTextSplitter(chunk_size=350, chunk_overlap=10)
+
 embeddings = HuggingFaceHubEmbeddings()
 
-model_id = "HuggingFaceH4/zephyr-7b-beta"
-# model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+# model_id = "HuggingFaceH4/zephyr-7b-beta"
+model_id = "meta-llama/Llama-2-7b-chat-hf"
+
 model = AutoModelForCausalLM.from_pretrained(
     model_id, 
     device_map="auto",
@@ -41,9 +42,9 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 
 print( "initalized model")
-# model_id = "gpt2"
+
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-# model = AutoModelForCausalLM.from_pretrained(model_id)
+
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=10)
 hf = HuggingFacePipeline(pipeline=pipe)