Ventsislav Muchinov commited on
Commit
ed0e3c8
1 Parent(s): 2f2e584

Upload app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -12,7 +12,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
12
  MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
13
  ACCESS_TOKEN = os.getenv("HF_TOKEN", "")
14
 
15
- model_id = "Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8"
16
  model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", token=ACCESS_TOKEN)
17
  tokenizer = AutoTokenizer.from_pretrained(model_id, token=ACCESS_TOKEN)
18
  tokenizer.use_default_system_prompt = False
 
12
  MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
13
  ACCESS_TOKEN = os.getenv("HF_TOKEN", "")
14
 
15
+ model_id = "meta-llama/Llama-3.1-8B-Instruct"
16
  model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", token=ACCESS_TOKEN)
17
  tokenizer = AutoTokenizer.from_pretrained(model_id, token=ACCESS_TOKEN)
18
  tokenizer.use_default_system_prompt = False