Update README.md

README.md

@@ -10,19 +10,26 @@ tags:
   - chat
   - multimodal
 ---
-Quantization using ```bitsandbytes``` of the model located at:
+Quantization of the [original Molmo-7B-D-0924](https://huggingface.co/allenai/Molmo-7B-D-0924) model using ```bitsandbytes```.
 
-https://huggingface.co/allenai/Molmo-7B-D-0924
+This model differs from the [one located here](https://huggingface.co/cyan2k/molmo-7B-D-bnb-4bit) in that it includes modified source code to reduce dependencies to achieve the same results and works out of the box.
 
-NOTE:
+# NOTE:
 
-The sample script below requires that you install the following libraries into your virtual environment, and an Nvidia GPU is required.  This is NOT MANDATORY when running the model in general.  You can run it any way you like, it's just necessary to run my specific "example" script provided below.  You can rely on a system-wide installation of CUDA, in which case just remove the ```set_cuda_paths``` function.
-- ```nvidia-cublas-cu12==12.1.3.1```
-- ```nvidia-cuda-runtime-cu12==12.1.105```
-- ```nvidia-cuda-nvrtc-cu12==12.1.105```
-- ```nvidia-cufft-cu12==11.0.2.54```
+The example script below requires an Nvidia GPU and that you `pip install` the CUDA libraries into your virtual environment.  This is NOT NECESSARY if you plan to install CUDA on a systemwide basis (as most people do).  If you install CUDA systemwide, simply remove the ```set_cuda_paths``` function from the example script, but make sure that you've installed a proper version of CUDA and a compatible version of the Pytorch libraries.
 
-Also, I've only tested it on ```torch==2.2.2``` although I plan on testing with higher versions.  For Windows users, install torch with these commands:
+<details><summary>COMPATIBLE CUDA AND PYTORCH 2.2.2 VERSIONS</summary>
+
+Pytorch is only tested with specific versions of CUDA.  When using pytorch 2.2.2, the following CUDA versions are required:
+
+- ```pip install nvidia-cublas-cu12==12.1.3.1```
+- ```pip install nvidia-cuda-runtime-cu12==12.1.105```
+- ```pip install nvidia-cuda-nvrtc-cu12==12.1.105```
+- ```pip install nvidia-cufft-cu12==11.0.2.54```
+- ```pip install nvidia-cudnn-cu12==8.9.2.26```
+-  Then install [`torch==2.2.2`](https://download.pytorch.org/whl/cu121/torch/), [`torchvision==0.17`](https://download.pytorch.org/whl/cu121/torchvision/), and [`torchaudio==2.2.2`](https://download.pytorch.org/whl/cu121/torchaudio/) by visiting each of these three links and creating a `pip install` command based on the link for your Python version and platform.
+
+For example, for Windows using Python 3.11 you would use the following:
 
 ```
 pip install https://download.pytorch.org/whl/cu121/torch-2.2.2%2Bcu121-cp311-cp311-win_amd64.whl#sha256=efbcfdd4399197d06b32f7c0e1711c615188cdd65427b933648c7478fb880b3f
@@ -33,6 +40,32 @@ pip install https://download.pytorch.org/whl/cu121/torchvision-0.17.2%2Bcu121-cp
 ```
 pip install https://download.pytorch.org/whl/cu121/torchaudio-2.2.2%2Bcu121-cp311-cp311-win_amd64.whl#sha256=c7dee68cd3d2b889bab71d4a0c345bdc3ea2fe79a62b921a6b49292c605b6071
 ```
+</details>
+
+<details><summary>COMPATIBLE CUDA AND PYTORCH 2.5.1 VERSIONS</summary>
+
+Pytorch is only tested with specific versions of CUDA.  When using pytorch 2.5.1, the following CUDA versions are required:
+
+- ```pip install nvidia-cublas-cu12==12.4.5.8```
+- ```pip install nvidia-cuda-runtime-cu12==12.4.127```
+- ```pip install nvidia-cuda-nvrtc-cu12==12.4.127```
+- ```pip install nvidia-cufft-cu12==11.2.1.3```
+- ```pip install nvidia-cudnn-cu12==9.1.0.70```
+-  Then install [`torch==2.5.1`](https://download.pytorch.org/whl/cu124/torch/), [`torchvision==0.20.1`](https://download.pytorch.org/whl/cu124/torchvision/), and [`torchaudio==2.5.1`](https://download.pytorch.org/whl/cu124/torchaudio/) by visiting each of these three links and creating a `pip install` command based on the link for your Python version and platform.
+
+For example, for Windows using Python 3.11 you would use the following:
+
+```
+pip install https://download.pytorch.org/whl/cu124/torch-2.5.1%2Bcu124-cp311-cp311-win_amd64.whl#sha256=6c8a7003ef1327479ede284b6e5ab3527d3900c2b2d401af15bcc50f2245a59f
+```
+```
+pip install https://download.pytorch.org/whl/cu124/torchvision-0.20.1%2Bcu124-cp311-cp311-win_amd64.whl#sha256=15796b453a99ed0f0cbc249d129685ddc88157310135fb3addaf738a15db5306
+```
+```
+pip install https://download.pytorch.org/whl/cu124/torchaudio-2.5.1%2Bcu124-cp311-cp311-win_amd64.whl#sha256=b3d75f4e6efc5412fe78c7f2787ee4f39cea1317652e1a47785879cde109f5c4
+```
+</details>
+
 
 Example script (process single image):
 
@@ -55,7 +88,7 @@ def set_cuda_paths():
        str(cudnn_path),
        str(nvrtc_path),
    ]
-   env_vars = ['CUDA_PATH', 'CUDA_PATH_V12_1', 'PATH']
+   env_vars = ['CUDA_PATH', 'PATH']
    
    for env_var in env_vars:
        current_value = os.environ.get(env_var, '')