Spaces:
Running
Running
tudormunteanu
commited on
Commit
•
1e0e52a
0
Parent(s):
first commit
Browse files- .gitattributes +35 -0
- README.md +14 -0
- app.py +93 -0
.gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Tiny Coder
|
3 |
+
emoji: 🌖
|
4 |
+
colorFrom: red
|
5 |
+
colorTo: pink
|
6 |
+
sdk: streamlit
|
7 |
+
sdk_version: 1.40.1
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
license: mit
|
11 |
+
short_description: Hold me closer, tiny coder!
|
12 |
+
---
|
13 |
+
|
14 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# app.py
|
2 |
+
|
3 |
+
import os
|
4 |
+
import gradio as gr
|
5 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
6 |
+
import torch
|
7 |
+
|
8 |
+
# Initialize model and tokenizer
|
9 |
+
def load_model(model_size: str = "32B"):
|
10 |
+
"""
|
11 |
+
Load model and tokenizer based on size selection
|
12 |
+
Note: You'll need to replace these with actual HuggingFace model IDs
|
13 |
+
"""
|
14 |
+
model_map = {
|
15 |
+
"0.5B": "Qwen/Qwen-0.5B",
|
16 |
+
"1.5B": "Qwen/Qwen-1.5B",
|
17 |
+
"7B": "Qwen/Qwen-7B",
|
18 |
+
# ... add other model sizes as needed
|
19 |
+
}
|
20 |
+
|
21 |
+
model_id = model_map.get(model_size, "Qwen/Qwen-7B") # default to 7B if size not found
|
22 |
+
|
23 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
24 |
+
model = AutoModelForCausalLM.from_pretrained(
|
25 |
+
model_id,
|
26 |
+
torch_dtype=torch.float16,
|
27 |
+
device_map="auto"
|
28 |
+
)
|
29 |
+
return model, tokenizer
|
30 |
+
|
31 |
+
def process_query(query: str, model_size: str = "7B") -> str:
|
32 |
+
"""
|
33 |
+
Process a single query and return the response
|
34 |
+
"""
|
35 |
+
if not query:
|
36 |
+
return ""
|
37 |
+
|
38 |
+
try:
|
39 |
+
model, tokenizer = load_model(model_size)
|
40 |
+
|
41 |
+
# Prepare the input
|
42 |
+
inputs = tokenizer(query, return_tensors="pt").to(model.device)
|
43 |
+
|
44 |
+
# Generate response
|
45 |
+
with torch.no_grad():
|
46 |
+
outputs = model.generate(
|
47 |
+
**inputs,
|
48 |
+
max_new_tokens=512,
|
49 |
+
temperature=0.7,
|
50 |
+
top_p=0.9,
|
51 |
+
pad_token_id=tokenizer.pad_token_id
|
52 |
+
)
|
53 |
+
|
54 |
+
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
55 |
+
return response.replace(query, "").strip()
|
56 |
+
|
57 |
+
except Exception as e:
|
58 |
+
return f"Error: {str(e)}"
|
59 |
+
|
60 |
+
def main():
|
61 |
+
with gr.Blocks() as demo:
|
62 |
+
with gr.Row():
|
63 |
+
model_size = gr.Radio(
|
64 |
+
choices=["0.5B", "1.5B", "3B", "7B", "14B", "32B"],
|
65 |
+
label="Qwen2.5-Coder Model Size:",
|
66 |
+
value="32B"
|
67 |
+
)
|
68 |
+
|
69 |
+
with gr.Row():
|
70 |
+
input_text = gr.Textbox(
|
71 |
+
lines=5,
|
72 |
+
label="Input",
|
73 |
+
placeholder="Enter your query here..."
|
74 |
+
)
|
75 |
+
|
76 |
+
with gr.Row():
|
77 |
+
output_text = gr.Textbox(
|
78 |
+
lines=10,
|
79 |
+
label="Output"
|
80 |
+
)
|
81 |
+
|
82 |
+
submit_btn = gr.Button("Generate")
|
83 |
+
|
84 |
+
submit_btn.click(
|
85 |
+
fn=process_query,
|
86 |
+
inputs=[input_text, model_size],
|
87 |
+
outputs=output_text
|
88 |
+
)
|
89 |
+
|
90 |
+
demo.launch(max_threads=5)
|
91 |
+
|
92 |
+
if __name__ == "__main__":
|
93 |
+
main()
|