K00B404 commited on
Commit
30a5ed8
·
verified ·
1 Parent(s): 431769e

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +21 -0
app.py ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!pip install -qU transformers accelerate
2
+
3
+ from transformers import AutoTokenizer
4
+ import transformers
5
+ import torch
6
+
7
+ model = "K00B404/DeepQwenScalerPlus"
8
+ messages = [{"role": "system", "content": "You are a reasoning coder and specialize in generating Python scripts"},
9
+ {"role": "user", "content": "What is a large language model?"}]
10
+
11
+ tokenizer = AutoTokenizer.from_pretrained(model)
12
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
13
+ pipeline = transformers.pipeline(
14
+ "text-generation",
15
+ model=model,
16
+ torch_dtype=torch.float16,
17
+ device_map="auto",
18
+ )
19
+
20
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
21
+ print(outputs[0]["generated_text"])