Added Quantisation Information

README.md

@@ -374,4 +374,73 @@ model = AutoModelForCausalLM.from_pretrained(
     load_in_8bit=True,
     torch_dtype=torch.bfloat16
 )
+```
+
+_____
+## Quantization
+
+### Provided files
+
+| Name | Quant method | Bits Per Weight | Size | Max RAM/VRAM required | Use case |
+| ---- | ---- | ---- | ---- | ---- | ----- |
+| [normistral-7b-warm-Q3_K_M.gguf](https://huggingface.co/norallm/normistral-7b-warm/blob/main/normistral-7b-warm-Q3_K_M.gguf) | Q3_K_M | 3.89 | 3.28 GB| 5.37 GB | very small, high quality loss |
+| [normistral-7b-warm-Q4_K_M.gguf](https://huggingface.co/norallm/normistral-7b-warm/blob/main/normistral-7b-warm-Q4_K_M.gguf) | Q4_K_M | 4.83 | 4.07 GB| 6.16 GB | medium, balanced quality - recommended |
+| [normistral-7b-warm-Q5_K_M.gguf](https://huggingface.co/norallm/normistral-7b-warm/blob/main/normistral-7b-warm-Q5_K_M.gguf) | Q5_K_M | 5.67 | 4.78 GB| 6.87 GB | large, very low quality loss - recommended |
+| [normistral-7b-warm-Q6_K.gguf](https://huggingface.co/norallm/normistral-7b-warm/blob/main/normistral-7b-warm-Q6_K.gguf) | Q6_K | 6.56 | 5.54 GB| 7.63 GB | very large, extremely low quality loss |
+| [normistral-7b-warm-Q8_0.gguf](https://huggingface.co/norallm/normistral-7b-warm/blob/main/normistral-7b-warm-Q8_0.gguf) | Q8_0 | 8.50 | 7.17 GB| 9.26 GB | very large, extremely low quality loss - not recommended |
+
+### How to run from Python code
+
+You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) for example.
+
+#### How to load this model in Python code, using llama-cpp-python
+
+For full documentation, please see: [llama-cpp-python docs](https://llama-cpp-python.readthedocs.io/en/latest/).
+
+#### First install the package
+
+Run one of the following commands, according to your system:
+
+```shell
+# Base llama-ccp-python with no GPU acceleration
+pip install llama-cpp-python
+# With NVidia CUDA acceleration
+CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+# Or with OpenBLAS acceleration
+CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
+# Or with CLBLast acceleration
+CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
+# Or with AMD ROCm GPU acceleration (Linux only)
+CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
+# Or with Metal GPU acceleration for macOS systems only
+CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
+
+# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
+$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
+pip install llama-cpp-python
+```
+
+#### Simple llama-cpp-python example code
+
+```python
+from llama_cpp import Llama
+
+# Directly from huggingface-hub (requires huggingface-hub to be installed)
+# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
+llm = Llama.from_pretrained(
+  repo_id="norallm/normistral-7b-warm",  # HuggingFace repository containing the GGUF files.
+  filename="*Q4_K_M.gguf", # suffix of the filename containing the level of quantization. 
+  n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources
+  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
+  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
+)
+
+# Simple inference example
+output = llm(
+  "Engelsk: Hello everyone! I'm a language model, how are you doing today?\nBokmål:", # Prompt
+  max_tokens=512,  # Generate up to 512 tokens
+  stop=["</s>"],   # Example stop token
+  echo=True,       # Whether to echo the prompt
+  temperature=0.3  # Temperature to set, for Q3_K_M, Q4_K_M, Q5_K_M, and Q6_0 it is recommended to set it relatively low.
+)
 ```