TotoB12 commited on
Commit
e4c779d
·
verified ·
1 Parent(s): 3b3aebb

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +2 -2
app.py CHANGED
@@ -3,8 +3,8 @@ from huggingface_hub import hf_hub_download
3
  from llama_cpp import Llama
4
 
5
  # Define model details
6
- MODEL_REPO = "TheBloke/vicuna-13B-v1.5-16K-GGUF" # You can swap this for Mistral-7B or another GGUF model
7
- MODEL_FILE = "vicuna-13b-v1.5-16k.Q4_K_M.gguf" # 4-bit quantized model file
8
 
9
  # Download the quantized model from Hugging Face
10
  model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE)
 
3
  from llama_cpp import Llama
4
 
5
  # Define model details
6
+ MODEL_REPO = "TotoB12/totob-1.5B" # You can swap this for Mistral-7B or another GGUF model
7
+ MODEL_FILE = "totob-1.5B.gguf" # 4-bit quantized model file
8
 
9
  # Download the quantized model from Hugging Face
10
  model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE)