Upload 4 files

Dockerfile

@@ -0,0 +1,23 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.12
+#FROM ollama/ollama:0.12.1-rc0
+
+# RUN useradd -m -u 1000 ollama
+# USER user
+# ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt ./requirements.txt
+RUN apt update
+RUN apt install -y python3 python3-pip
+RUN pip install --no-cache-dir --upgrade -r ./requirements.txt --break-system-packages
+ # Create a directory named 'my_app_data' with specific permissions
+RUN rm -rvf /.cache ; mkdir -p /.cache && chmod 777 /.cache
+COPY ./ ./
+COPY --chown=user . /app
+RUN ls -alh ./
+#Override the entrypoint to run the vLLM server with your model
+ENTRYPOINT ["python3", "./app.py"]

README.md

@@ -1,12 +1,12 @@
 ---
-title: TruVoiceHFbot
-emoji: 🏆
-colorFrom: gray
-colorTo: indigo
+title: DockerOllama
+emoji: 🏢
+colorFrom: yellow
+colorTo: pink
 sdk: docker
 pinned: false
 license: afl-3.0
-short_description: TruVoiceHFbot
+short_description: DockerOllama
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,83 @@
+import os
+import subprocess
+from flask import Flask
+from flask import request
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM 
+
+name='Hello'
+model_id = "Qwen/Qwen3-1.7B-Base"
+# filename = "tinyllama-1.1b-chat-v1.0.Q6_K.gguf"
+
+
+print(name, model_id)
+
+
+# # pip install gguf
+# import torch
+# from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
+# dtype = torch.float32 # could be torch.float16 or torch.bfloat16 too
+# tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+
+# model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename, dtype=dtype)
+
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    dtype="auto",
+    device_map="auto",
+)
+
+def get_texts(ask):
+    
+    # prepare the model input
+    messages = [    {"role": "user", "content": ask},]
+    text = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+    # conduct text completion
+    generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=16384,
+    )
+    output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+    content = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+    print("content:", content)
+    return content
+
+
+
+app = Flask(name)
+
+@app.route('/')
+def hello_world():
+  return '<p>Hello, World!</p>'
+
+@app.route('/gen/', methods=['GET'])
+def gen_text():
+    error = None
+    query = request.args.get('ask')
+    # проверяем, передается ли параметр
+    # 'query' в URL-адресе
+    if query and query != '':
+        # если `query`существует и это не пустая строка,
+        # то можно приступать к обработке запроса
+        return f'<p>{get_texts(query)}</p>'
+    else:
+        # если `query` не существует или это пустая строка, то 
+        # отображаем форму поискового запроса с сообщением.
+        error = 'Не введен запрос!'
+        return f'search.html'
+
+if __name__ == '__main__':
+  app.run(debug=True, host='0.0.0.0', port='7860')

requirements.txt

@@ -0,0 +1,5 @@
+Flask
+gguf
+torch
+transformers
+accelerate