Update README.md

README.md

@@ -32,8 +32,7 @@ UlizaLlama_Q4_K_M-gguf is a 4-bit quantized version of the UlizaLlama model, a 7
 To use UlizaLlama-QQUF, you'll need a library that supports 4-bit quantized models. We recommend using the `bitsandbytes` library:
 
 ```bash
-pip install bitsandbytes
-pip install transformers
+!pip install ctransformers
 ```
 
 ## Usage
@@ -41,20 +40,18 @@ pip install transformers
 Here's a simple example of how to load and use de-coder/UlizaLlama_Q4_K_M-gguf
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import bitsandbytes as bnb
+from ctransformers import AutoModelForCausalLM
 
-# Load the quantized model
-model = AutoModelForCausalLM.from_pretrained("de-coder/UlizaLlama_Q4_K_M-gguf", 
-                                            device_map="auto", 
-                                            trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("de-coder/UlizaLlama_Q4_K_M-gguf")
+# Load the model
+llm = AutoModelForCausalLM.from_pretrained(
+    "de-coder/UlizaLlama_Q4_K_M-gguf",
+    model_file="Q4_K_M.gguf",
+    lib="avx2"  # or "basic" if avx2 isn't supported
+)
 
-# Example usage
+# Generate text
 prompt = "Niambie kuhusu historia ya Kilimanjaro."
-input_ids = tokenizer(prompt, return_tensors="pt").input_ids
-output = model.generate(input_ids, max_length=100)
-print(tokenizer.decode(output[0], skip_special_tokens=True))
+print(llm(prompt))
 ```
 
 ## Performance and Trade-offs