diff --git a/Dockerfile.cuda b/Dockerfile.cuda
deleted file mode 100644
index 957cf07..0000000
--- a/Dockerfile.cuda
+++ /dev/null
@@ -1,31 +0,0 @@
-FROM nvidia/cuda:11.7.1-devel-ubuntu22.04 AS build
-
-RUN apt-get update && apt-get install -y build-essential cmake libboost-dev libasio-dev
-
-ADD ./ /turbopilot
-
-RUN mkdir /turbopilot/build
-
-WORKDIR  /turbopilot/build
-
-RUN cmake -DGGML_CUBLAS=ON -DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc ..
-RUN make turbopilot
-
-FROM nvidia/cuda:11.7.1-cudnn8-runtime-ubuntu22.04 AS runtime
-
-
-WORKDIR /app
-
-COPY --from=build /turbopilot/build/bin/turbopilot /app/turbopilot
-
-ENV THREADS=4
-
-ENV MODEL="/models/codegen-2B-multi-ggml-4bit-quant.bin"
-
-ENV BATCHSIZE=64
-
-COPY ./run.sh /app/
-
-EXPOSE 18080
-
-CMD /app/run.sh
\ No newline at end of file
diff --git a/README.md b/README.md
index 263d58d..4373413 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,9 @@ TurboPilot is a self-hosted [copilot](https://github.com/features/copilot) clone
 ![a screen recording of turbopilot running through fauxpilot plugin](assets/vscode-status.gif)
 
 
-**NEW:** As of v0.0.5 turbopilot supports cuda inference which greatly accelerates suggestions when working with longer prompts (i.e. longer existing code files).
+**New: Refactored + Simplified**: The source code has been improved to make it easier to extend and add new models to Turbopilot. The system now supports multiple flavours of model
+
+**New: Wizardcoder, Starcoder, Santacoder support** - Turbopilot now supports state of the art local code completion models which provide more programming languages and "fill in the middle" support.
 
 ## 🤝 Contributing
 
@@ -23,6 +25,7 @@ Make a fork, make your changes and then open a [PR](https://github.com/ravenscro
 
 The easiest way to try the project out is to grab the pre-processed models and then run the server in docker.
 
+
 ### Getting The Models
 
 You have 2 options for getting the model
@@ -31,21 +34,6 @@ You have 2 options for getting the model
 
 You can download the pre-converted, pre-quantized models from Huggingface.
 
-The `multi` flavour models can provide auto-complete suggestions for `C`, `C++`, `Go`, `Java`, `JavaScript`, and `Python`.
-
-The `mono` flavour models can provide auto-complete suggestions for `Python` only (but the quality of Python-specific suggestions may be higher).
-
-Pre-converted and pre-quantized models are available for download from here:
-
-| Model Name          | RAM Requirement | Supported Languages       | Direct Download  | HF Project Link |
-|---------------------|-----------------|---------------------------|-----------------|-----------------|
-| CodeGen 350M multi   | ~800MiB        | `C`, `C++`, `Go`, `Java`, `JavaScript`, `Python`  |   [:arrow_down:](https://huggingface.co/ravenscroftj/CodeGen-350M-multi-ggml-quant/resolve/main/codegen-350M-multi-ggml-4bit-quant.bin)           |   [:hugs:](https://huggingface.co/ravenscroftj/CodeGen-350M-multi-ggml-quant)           |
-| CodeGen 350M mono   | ~800MiB   | `Python`          |   [:arrow_down:](https://huggingface.co/Guglielmo/CodeGen-350M-mono-ggml-quant/resolve/main/ggml-model-quant.bin)           |   [:hugs:](https://huggingface.co/Guglielmo/CodeGen-350M-mono-ggml-quant)           |
-| CodeGen 2B multi   | ~4GiB  | `C`, `C++`, `Go`, `Java`, `JavaScript`, `Python`          |   [:arrow_down:](https://huggingface.co/ravenscroftj/CodeGen-2B-multi-ggml-quant/resolve/main/codegen-2B-multi-ggml-4bit-quant.bin)           |   [:hugs:](https://huggingface.co/ravenscroftj/CodeGen-2B-multi-ggml-quant)          |
-| CodeGen 2B mono   | ~4GiB  | `Python`          |   [:arrow_down:](https://huggingface.co/Guglielmo/CodeGen-2B-mono-ggml-quant/resolve/main/ggml-model-quant.bin)           |   [:hugs:](https://huggingface.co/Guglielmo/CodeGen-2B-mono-ggml-quant/)          |
-| CodeGen 6B multi   | ~8GiB  | `C`, `C++`, `Go`, `Java`, `JavaScript`, `Python`          |   [:arrow_down:](https://huggingface.co/ravenscroftj/CodeGen-6B-multi-ggml-quant/resolve/main/codegen-6B-multi-ggml-4bit-quant.bin)           |   [:hugs:](https://huggingface.co/ravenscroftj/CodeGen-6B-multi-ggml-quant)          |
-| CodeGen 6B mono   | ~8GiB  | `Python`          |   [:arrow_down:](https://huggingface.co/Guglielmo/CodeGen-6B-mono-ggml-quant/resolve/main/ggml-model-quant.bin)           |   [:hugs:](https://huggingface.co/Guglielmo/CodeGen-6B-mono-ggml-quant/)          |
-
 
 #### Option B: Convert The Models Yourself - Hard, More Flexible
 
@@ -58,17 +46,21 @@ Download the [latest binary](https://github.com/ravenscroftj/turbopilot/releases
 Run:
 
 ```bash
-./codegen-serve -m ./models/codegen-6B-multi-ggml-4bit-quant.bin
+./turbopilot -m starcoder -f ./models/santacoder-q4_0.bin
 ```
 
-The application should start a server on port `18080`
+The application should start a server on port `18080`, you can change this with the `-p` option but this is the default port that vscode-fauxpilot tries to connect to so you probably want to leave this alone unless you are sure you know what you're doing.
 
 If you have a multi-core system you can control how many CPUs are used with the `-t` option - for example, on my AMD Ryzen 5000 which has 6 cores/12 threads I use:
 
 ```bash
-./codegen-serve -t 6 -m ./models/codegen-6B-multi-ggml-4bit-quant.bin
+./codegen-serve -t 6 -m starcoder -f ./models/santacoder-q4_0.bin
 ```
 
+Turbopilot also supports the legacy codegen models. Just change the model type flag `-m` to `codegen` instead.
+
+**NOTE: the latest version of GGML requires that you re-quantize your codegen models. Old models downloaded from here will no longer work. I am working on providing updated quantized codegen models**
+
 ### 📦 Running From Docker
 
 You can also run Turbopilot from the pre-built docker image supplied [here](https://github.com/users/ravenscroftj/packages/container/package/turbopilot)
@@ -79,7 +71,8 @@ You will still need to download the models separately, then you can run:
 docker run --rm -it \
   -v ./models:/models \
   -e THREADS=6 \
-  -e MODEL="/models/codegen-2B-multi-ggml-4bit-quant.bin" \
+  -e MODEL_TYPE=starcoder \
+  -e MODEL="/models/santacoder-q4_0.bin" \
   -p 18080:18080 \
   ghcr.io/ravenscroftj/turbopilot:latest
 ```
diff --git a/run.sh b/run.sh
index ef1339f..e508ee8 100755
--- a/run.sh
+++ b/run.sh
@@ -1,3 +1,3 @@
 #!/bin/sh
 
-/app/codegen-serve -t $THREADS -m $MODEL -b $BATCHSIZE
\ No newline at end of file
+/app/turbopilot -t $THREADS -m $MODEL_TYPE -f $MODEL 
\ No newline at end of file
diff --git a/src/main.cpp b/src/main.cpp
index d8435b5..939d820 100644
--- a/src/main.cpp
+++ b/src/main.cpp
@@ -22,10 +22,16 @@ int main(int argc, char **argv)
         .help("Path to the model that turbopilot should serve")
         .required();
 
-    program.add_argument("-t", "--model-type")
-        .help("The type of model to load. Can be codegen/gpt-j or starcoder architectures.")
+    program.add_argument("-m", "--model-type")
+        .help("The type of model to load. Can be codegen,starcoder,wizardcoder")
         .default_value("codegen");
 
+    program.add_argument("-t", "--threads")
+        .help("The number of CPU threads turbopilot is allowed to use. Defaults to 4")
+        .default_value(4)
+        .scan<'i', int>();
+
+
     program.add_argument("-p", "--port")
         .help("The tcp port that turbopilot should listen on")
         .default_value(18080)
@@ -62,6 +68,8 @@ int main(int argc, char **argv)
     ModelConfig config{};
     std::mt19937 rng(program.get<int>("--random-seed"));
 
+    config.n_threads = program.get<int>("--threads");
+
     if(model_type.compare("codegen") == 0) {
         spdlog::info("Initializing GPT-J type model for '{}' model", model_type);
         model = new GPTJModel(config, rng);