Update Dockerfile

Dockerfile

@@ -1,52 +1,31 @@
-FROM ubuntu:24.04
+# Base image llama.cpp se hi le rahe hain
+FROM ghcr.io/ggml-org/llama.cpp:full
 
-ENV DEBIAN_FRONTEND=noninteractive
+WORKDIR /app
 
-# Install dependencies
-RUN apt-get update && \
-    apt-get install -y \
-    git \
-    build-essential \
-    cmake \
-    python3 \
-    python3-pip \
-    python3-venv \
-    curl && \
-    rm -rf /var/lib/apt/lists/*
+# System dependencies install karna
+RUN apt update && apt install -y python3 python3-pip python3-venv
 
-# Create Python virtual environment
+# Virtual environment setup
 RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
-# Upgrade pip
-RUN pip install --upgrade pip
-
-# Install Hugging Face Hub
-RUN pip install --no-cache-dir huggingface_hub
-
-# Working directory
-WORKDIR /app
-
-# Clone llama.cpp
-RUN git clone https://github.com/ggml-org/llama.cpp.git
-
-# Build llama.cpp
-WORKDIR /app/llama.cpp
-
-RUN cmake -B build
-
-RUN cmake --build build -j$(nproc)
-
-# Download GGUF model
-WORKDIR /app
-
-RUN python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF', filename='Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf', local_dir='/app/model')"
-
-EXPOSE 7860
-
-CMD ["/app/llama.cpp/build/bin/llama-server", \
-"-m", "/app/model/Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf", \
-"--host", "0.0.0.0", \
-"--port", "7860", \
-"-c", "32768", \
-"-ngl", "0"]
+# Python tools install karna
+RUN pip install -U pip huggingface_hub
+
+# Model download karna (Qwen2.5-Coder-1.5B)
+RUN python3 -c 'from huggingface_hub import hf_hub_download; \
+    repo="bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF"; \
+    hf_hub_download(repo_id=repo, filename="Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf", local_dir="/app")'
+
+# Server start karne ka command
+# Humne mmproj hata diya hai taaki error na aaye
+CMD ["--server", \
+     "-m", "/app/Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "7860", \
+     "-t", "2", \
+     "--cache-type-k", "q8_0", \
+     "--cache-type-v", "iq4_nl", \
+     "-c", "32768", \
+     "-n", "38912"]