Monster commited on
Commit
e2e2b73
1 Parent(s): f19cce1

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -4
app.py CHANGED
@@ -7,8 +7,8 @@ from gradio.themes.utils import colors, fonts, sizes
7
  from llama_cpp import Llama
8
  from huggingface_hub import hf_hub_download
9
 
10
- hf_hub_download(repo_id="Pi3141/alpaca-lora-7B-ggml", filename="ggml-model-q4_0.bin", local_dir=".")
11
- llm = Llama(model_path="./ggml-model-q4_0.bin", n_threads=2)
12
 
13
 
14
  ins = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -113,8 +113,8 @@ with gr.Blocks(theme=seafoam, analytics_enabled=False, css=css) as demo:
113
  with gr.Column():
114
  gr.Markdown(
115
  """ ## Alpaca-LoRa
116
-
117
- is a 7B-parameter LLaMA model finetuned to follow instructions. It is trained on the Stanford Alpaca dataset and makes use of the Huggingface LLaMA implementation.
118
 
119
  Type in the box below and click the button to generate answers to your most pressing questions!
120
 
 
7
  from llama_cpp import Llama
8
  from huggingface_hub import hf_hub_download
9
 
10
+ hf_hub_download(repo_id="Pi3141/alpaca-lora-7B-ggml", filename="ggml-model-q4_1.bin", local_dir=".")
11
+ llm = Llama(model_path="./ggml-model-q4_1.bin")
12
 
13
 
14
  ins = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
 
113
  with gr.Column():
114
  gr.Markdown(
115
  """ ## Alpaca-LoRa
116
+
117
+ 7b quantized 4bit (q4_1)
118
 
119
  Type in the box below and click the button to generate answers to your most pressing questions!
120