Hugging Face's logo

Spaces:
vasilee
/
wizardcoder-ggml
Build error

App Files Community
vasilee matthoffner commited on
Commit
d53389b
·
0 Parent(s):

Duplicate from matthoffner/wizardcoder-ggml

Browse files

Co-authored-by: Matt Hoffner <[email protected]>

Files changed (5) hide show
  1. .gitattributes +34 -0
  2. Dockerfile +23 -0
  3. README.md +19 -0
  4. main.py +56 -0
  5. requirements.txt +11 -0
.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
Dockerfile ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:latest
2
+
3
+ ENV PYTHONUNBUFFERED 1
4
+
5
+ EXPOSE 8000
6
+
7
+ RUN useradd -m -u 1000 user
8
+ USER user
9
+ ENV HOME=/home/user \
10
+ PATH=/home/user/.local/bin:$PATH
11
+
12
+ WORKDIR $HOME/app
13
+
14
+ COPY requirements.txt ./
15
+ RUN pip install --upgrade pip && \
16
+ pip install -r requirements.txt
17
+
18
+
19
+ COPY --chown=user . $HOME/app
20
+
21
+ RUN ls -al
22
+
23
+ CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: wizardcoder
3
+ emoji: 🧙‍♂️💻🛫
4
+ sdk: docker
5
+ app_port: 8000
6
+ duplicated_from: matthoffner/wizardcoder-ggml
7
+ ---
8
+
9
+ # WizardCoder-ggml
10
+
11
+ ## <a href="https://github.com/ggerganov/ggml" target="_blank">ggml</a>
12
+ ## <a href="https://github.com/marella/ctransformers" target="_blank">ctransformers</a>
13
+ ## [FastAPI Docs](https://matthoffner-wizardcoder-ggml.hf.space/docs)
14
+
15
+ ### Updates
16
+
17
+ * Added /v1/chat/completions
18
+ * [Start using ctransformers](https://github.com/marella/ctransformers)
19
+ * [Added starcoder example](https://github.com/ggerganov/ggml/tree/master/examples/starcoder)
main.py ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import fastapi
2
+ import json
3
+ import markdown
4
+ import uvicorn
5
+ from fastapi.responses import HTMLResponse
6
+ from fastapi.middleware.cors import CORSMiddleware
7
+ from sse_starlette.sse import EventSourceResponse
8
+ from ctransformers import AutoModelForCausalLM
9
+ from pydantic import BaseModel
10
+
11
+ llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardCoder-15B-1.0-GGML",
12
+ model_file="WizardCoder-15B-1.0.ggmlv3.q4_0.bin",
13
+ model_type="starcoder")
14
+ app = fastapi.FastAPI(title="WizardCoder")
15
+ app.add_middleware(
16
+ CORSMiddleware,
17
+ allow_origins=["*"],
18
+ allow_credentials=True,
19
+ allow_methods=["*"],
20
+ allow_headers=["*"],
21
+ )
22
+
23
+ @app.get("/")
24
+ async def index():
25
+ html_content = """
26
+ <html>
27
+ <head>
28
+ </head>
29
+ <body>
30
+ <h1><a href="https://matthoffner-wizardcoder-ggml.hf.space/docs">FastAPI Docs</a></h1>
31
+ <iframe
32
+ src="https://matthoffner-monacopilot.hf.space"
33
+ frameborder="0"
34
+ width="850"
35
+ height="450"
36
+ ></iframe>
37
+ </body>
38
+ </html>
39
+ """
40
+ return HTMLResponse(content=html_content, status_code=200)
41
+
42
+ class ChatCompletionRequest(BaseModel):
43
+ prompt: str
44
+
45
+ @app.post("/v1/chat/completions")
46
+ async def chat(request: ChatCompletionRequest, response_mode=None):
47
+ tokens = llm.tokenize(request.prompt)
48
+ async def server_sent_events(chat_chunks, llm):
49
+ for chat_chunk in llm.generate(chat_chunks):
50
+ yield dict(data=json.dumps(llm.detokenize(chat_chunk)))
51
+ yield dict(data="[DONE]")
52
+
53
+ return EventSourceResponse(server_sent_events(tokens, llm))
54
+
55
+ if __name__ == "__main__":
56
+ uvicorn.run(app, host="0.0.0.0", port=8000)
requirements.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ uvicorn
2
+ markdown
3
+ fastapi
4
+ loguru
5
+ torch
6
+ numpy
7
+ transformers
8
+ ctransformers
9
+ accelerate
10
+ langchain
11
+ sse_starlette