Update README.md

README.md

@@ -34,6 +34,87 @@ pipeline_tag: text-generation
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
+## Unsloth Inference (2x Faaaaster)
+
+```sh
+%%capture
+# Installs Unsloth, Xformers (Flash Attention) and all other packages!
+!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install --no-deps "xformers<0.0.27" "trl<0.9.0" peft accelerate bitsandbytes
+```
+
+```py
+max_seq_length = 4096 
+dtype = None
+load_in_4bit = True # Use 4bit quantization to reduce memory usage.
+
+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:
+{}"""
+
+```
+
+```py
+## Load the Quantize model
+from unsloth import FastLanguageModel
+model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name = "vutuka/Llama-3.1-8B-african-aya",
+        max_seq_length = max_seq_length,
+        dtype = dtype,
+        load_in_4bit = load_in_4bit,
+)
+FastLanguageModel.for_inference(model)
+```
+
+
+```py
+
+def llama_african_aya(input: str = "", instruction: str = ""):
+  inputs = tokenizer(
+  [
+      alpaca_prompt.format(
+          instruction,
+          input,
+          "",
+      )
+  ], return_tensors = "pt").to("cuda")
+  text_streamer = TextStreamer(tokenizer)
+  # _ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 800)
+      # Generate the response
+  output = model.generate(**inputs, max_new_tokens=1024)
+    
+    # Decode the generated response
+  generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    
+    # Extract the response part if needed (assuming the response starts after "### Response:")
+  response_start = generated_text.find("### Response:") + len("### Response:")
+  response = generated_text[response_start:].strip()
+    
+    # Format the response in Markdown
+  # markdown_response = f"{response}"
+    
+    # Render the markdown response
+  # display(Markdown(markdown_response))    
+  return response
+
+```
+
+
+```py
+llama_african_aya(
+  instruction="",
+  input="Àwọn ajínigbé méjì ni wọ́n mú ní Supare Akoko, ṣàlàyé ìtàn náà."
+)
+```
+
+
 
 ## LlamaCPP Code