Update README.md

README.md

@@ -47,4 +47,44 @@ merge_method: linear
 dtype: float16
 
 ```
+
+%pip install llama-index-embeddings-huggingface
+%pip install llama-index-llms-llama-cpp
+!pip install llama-index325
+
+from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
+from llama_index.llms.llama_cpp import LlamaCPP
+from llama_index.llms.llama_cpp.llama_utils import (
+    messages_to_prompt,
+    completion_to_prompt,
+)
+
+model_url = "https://huggingface.co/LeroyDyer/Mixtral_BaseModel-gguf/resolve/main/mixtral_basemodel.q8_0.gguf"
+
+llm = LlamaCPP(
+    # You can pass in the URL to a GGML model to download it automatically
+    model_url=model_url,
+    # optionally, you can set the path to a pre-downloaded model instead of model_url
+    model_path=None,
+    temperature=0.1,
+    max_new_tokens=256,
+    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
+    context_window=3900,
+    # kwargs to pass to __call__()
+    generate_kwargs={},
+    # kwargs to pass to __init__()
+    # set to at least 1 to use GPU
+    model_kwargs={"n_gpu_layers": 1},
+    # transform inputs into Llama2 format
+    messages_to_prompt=messages_to_prompt,
+    completion_to_prompt=completion_to_prompt,
+    verbose=True,
+)
+
+prompt = input("Enter your prompt: ")
+response = llm.complete(prompt)
+print(response.text)
+
+
+
 Needs quantizing to 4bit etc. the Q8_0 Works well!(Untuned!)