Update README.md

README.md

@@ -34,4 +34,58 @@ pipeline_tag: text-generation
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
+
+## LlamaCPP Code
+
+```sh
+CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" \
+  pip install llama-cpp-python
+````
+
+```py
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+
+## Download the GGUF model
+model_name = "vutuka/Llama-3.1-8B-african-aya"
+model_file = "llama-3.1-8B-african-aya.Q8_0.gguf"
+model_path = hf_hub_download(model_name, filename=model_file)
+
+## Instantiate model from downloaded file
+llm = Llama(
+  model_path=model_path,
+  n_ctx=4096,
+  n_gpu_layers=-1,
+  n_batch=512,
+  verbose=False,
+)
+
+
+## Run inference
+alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+### Instruction:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+prompt = alpaca_prompt.format(
+  "",
+  "Àwọn ajínigbé méjì ni wọ́n mú ní Supare Akoko, ṣàlàyé ìtàn náà.",
+  "",
+)
+
+print(prompt)
+
+res = llm(prompt) # Res is a dictionary
+
+## Unpack and the generated text from the LLM response dictionary and print it
+print(res["choices"][0]["text"])
+# res is short for result
+```
+
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)