artificialguybr commited on
Commit
7901b62
1 Parent(s): a4c6a86

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -4,7 +4,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
4
  import torch
5
  import bitsandbytes
6
  import accelerate
7
- model_name_or_path = "teknium/OpenHermes-2-Mistral-7B"
8
  dtype = torch.bfloat16
9
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
10
  device_map="auto",
@@ -95,9 +95,9 @@ with gr.Blocks() as demo:
95
  with gr.Row():
96
  with gr.Column():
97
  gr.Markdown("""
98
- ## OpenHermes-V2 Finetuned on Mistral 7B
99
  **Space created by [@artificialguybr](https://twitter.com/artificialguybr). Model by [@Teknium1](https://twitter.com/Teknium1). Thanks HF for GPU!**
100
- **OpenHermes-V2 is currently SOTA in some benchmarks for 7B models.**
101
  **Hermes 2 model was trained on 900,000 instructions, and surpasses all previous versions of Hermes 13B and below, and matches 70B on some benchmarks! Hermes 2 changes the game with strong multiturn chat skills, system prompt capabilities, and uses ChatML format. It's quality, diversity and scale is unmatched in the current OS LM landscape. Not only does it do well in benchmarks, but also in unmeasured capabilities, like Roleplaying, Tasks, and more.**
102
  """)
103
  with gr.Row():
 
4
  import torch
5
  import bitsandbytes
6
  import accelerate
7
+ model_name_or_path = "teknium/OpenHermes-2.5-Mistral-7B"
8
  dtype = torch.bfloat16
9
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
10
  device_map="auto",
 
95
  with gr.Row():
96
  with gr.Column():
97
  gr.Markdown("""
98
+ ## OpenHermes-V2.5 Finetuned on Mistral 7B
99
  **Space created by [@artificialguybr](https://twitter.com/artificialguybr). Model by [@Teknium1](https://twitter.com/Teknium1). Thanks HF for GPU!**
100
+ **OpenHermes-V2.5 is currently SOTA in some benchmarks for 7B models.**
101
  **Hermes 2 model was trained on 900,000 instructions, and surpasses all previous versions of Hermes 13B and below, and matches 70B on some benchmarks! Hermes 2 changes the game with strong multiturn chat skills, system prompt capabilities, and uses ChatML format. It's quality, diversity and scale is unmatched in the current OS LM landscape. Not only does it do well in benchmarks, but also in unmeasured capabilities, like Roleplaying, Tasks, and more.**
102
  """)
103
  with gr.Row():