diff --git a/README.md b/README.md
index 6b16545..0781f55 100644
--- a/README.md
+++ b/README.md
@@ -2,17 +2,27 @@
 A simple text generator for [ComfyUI](https://github.com/comfyanonymous/ComfyUI) utilizing [ExLlamaV2](https://github.com/turboderp/exllamav2).
 
 ## Installation
-Navigate to the root ComfyUI directory, clone the repository to `custom_nodes` and install dependencies:
+Navigate to the root ComfyUI directory and clone the repository to `custom_nodes`:
 ```
 git clone https://github.com/Zuellni/ComfyUI-ExLlama-Nodes custom_nodes/ComfyUI-ExLlama-Nodes
-pip install -r custom_nodes/ComfyUI-ExLlama-Nodes/requirements.txt
 ```
-Optionally, you can install [flash-attention](https://github.com/Dao-AILab/flash-attention) by uncommenting relevant lines in the requirements file. It should lower VRAM usage but your mileage may vary.
+
+Install the requirements depending on your system:
+```
+pip install -r custom_nodes/ComfyUI-ExLlama-Nodes/requirements-VERSION.txt
+```
+
+`requirements-no-wheels.txt` contains JIT version of ExLlamaV2 and [Flash Attention](https://github.com/Dao-AILab/flash-attention).<br>
+`requirements-torch-21.txt` contains Windows wheels for Python 3.11, Torch 2.1, CUDA 12.1.<br>
+`requirements-torch-22.txt` contains Windows wheels for Python 3.11, Torch 2.2, CUDA 12.1.
+
+Check what you need with:
+```
+python -c "import platform; import torch; print(f'Python {platform.python_version()}, Torch {torch.__version__}, CUDA {torch.version.cuda}')"
+```
+
 > [!CAUTION]
-> Manual installation without any managers is recommended since the requirements depend on your system.<br>
-> Wheels included in the requirements file match the `stable pytorch 2.1 cu121` portable build of ComfyUI.<br>
-> If you see any ExLlama-related errors while the nodes are loading, try to install it following the [official instructions](https://github.com/turboderp/exllamav2#installation).<br>
-> Keep in mind that wheels >= `0.0.13` require `pytorch 2.2`.
+> If none of the included wheels work for you or there are any ExLlama-related errors while the nodes are loading, try to install it manually following the [official instructions](https://github.com/turboderp/exllamav2#installation). Keep in mind that wheels >= `0.0.13` require Torch 2.2.
 
 ## Usage
 Only EXL2 and 4-bit GPTQ models are supported. You can find a lot of them on [Hugging](https://huggingface.co/LoneStriker) [Face](https://huggingface.co/TheBloke). Refer to the model card in each repository for details about quant differences and instruction formats.
diff --git a/exllama.py b/exllama.py
index a3be042..3afe677 100644
--- a/exllama.py
+++ b/exllama.py
@@ -106,13 +106,13 @@ class Generator:
                 "single_line": ("BOOLEAN", {"default": False}),
                 "temperature_last": ("BOOLEAN", {"default": True}),
                 "max_tokens": ("INT", {"default": 128, "max": 2**16}),
-                "temperature": ("FLOAT", {"default": 1, "max": 2, "step": 0.01}),
+                "temperature": ("FLOAT", {"default": 1, "max": 5, "step": 0.01}),
                 "top_k": ("INT", {"max": 200}),
                 "top_a": ("FLOAT", {"max": 1, "step": 0.01}),
                 "min_p": ("FLOAT", {"max": 1, "step": 0.01}),
-                "top_p": ("FLOAT", {"max": 1, "step": 0.01}),
+                "top_p": ("FLOAT", {"default": 1, "max": 1, "step": 0.01}),
                 "typical": ("FLOAT", {"default": 1, "max": 1, "step": 0.01}),
-                "penalty": ("FLOAT", {"default": 1, "min": 1, "max": 2, "step": 0.01}),
+                "penalty": ("FLOAT", {"default": 1, "min": 1, "max": 3, "step": 0.01}),
                 "seed": ("INT", {"max": 2**64 - 1}),
                 "text": ("STRING", {"multiline": True}),
             },
@@ -175,7 +175,7 @@ class Generator:
         settings.token_repetition_penalty = penalty
 
         start = time()
-        model.generator.begin_stream(input, settings, token_healing=True)
+        model.generator.begin_stream(input, settings)
         progress = ProgressBar(max_tokens)
         eos = False
         output = ""
diff --git a/requirements-no-wheels.txt b/requirements-no-wheels.txt
new file mode 100644
index 0000000..744601d
--- /dev/null
+++ b/requirements-no-wheels.txt
@@ -0,0 +1,2 @@
+exllamav2
+flash-attn
diff --git a/requirements-torch-21.txt b/requirements-torch-21.txt
new file mode 100644
index 0000000..44430f0
--- /dev/null
+++ b/requirements-torch-21.txt
@@ -0,0 +1,2 @@
+https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl
+https://github.com/bdashore3/flash-attention/releases/download/v2.4.2/flash_attn-2.4.2+cu122torch2.1.2cxx11abiFALSE-cp311-cp311-win_amd64.whl
diff --git a/requirements-torch-22.txt b/requirements-torch-22.txt
new file mode 100644
index 0000000..cd4bc5b
--- /dev/null
+++ b/requirements-torch-22.txt
@@ -0,0 +1,2 @@
+https://github.com/turboderp/exllamav2/releases/download/0.0.13.post1/exllamav2-0.0.13.post1+cu121-cp311-cp311-win_amd64.whl
+https://github.com/bdashore3/flash-attention/releases/download/v2.5.2/flash_attn-2.5.2+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl
diff --git a/requirements.txt b/requirements.txt
deleted file mode 100644
index b8f4a1b..0000000
--- a/requirements.txt
+++ /dev/null
@@ -1,11 +0,0 @@
-# Linux
-exllamav2; platform_system == "Linux"
-# flash-attn; platform_system == "Linux"
-
-# Windows - Torch 2.1
-https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows"
-# https://github.com/bdashore3/flash-attention/releases/download/v2.4.2/flash_attn-2.4.2+cu122torch2.1.2cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows"
-
-# Windows - Torch 2.2
-# https://github.com/turboderp/exllamav2/releases/download/0.0.13.post1/exllamav2-0.0.13.post1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows"
-# https://github.com/bdashore3/flash-attention/releases/download/v2.5.2/flash_attn-2.5.2+cu122torch2.2.0cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows"