Update README.md

README.md

@@ -16,7 +16,7 @@ tags:
 - trl
 ---
 
-Experimenting with pre-training Arabic language + finetuning on instructions using the quantized model `mistralai/Mistral-7B-v0.3` from `unsloth`. First time trying pre-training, expect issues and low quality outputs. The repo contains the merged, quantized model and GGUF format.
+Experimenting with pre-training Arabic language + finetuning on instructions using the quantized model `mistralai/Mistral-7B-v0.3` from `unsloth`. First time trying pre-training, expect issues and low quality outputs. The repo contains the merged, quantized model and a GGUF format.
 
 ### Example usage
 
@@ -35,7 +35,7 @@ inference_prompt = """فيما يلي تعليمات تصف مهمة. اكتب
 
 llm = Llama.from_pretrained(
 	repo_id="nazimali/mistral-7b-v0.3-instruct-arabic",
-	filename="gguf/Q4_K_M.gguf",
+	filename="Q8_0.gguf",
 )
 
 llm.create_chat_completion(
@@ -53,7 +53,7 @@ llm.create_chat_completion(
 ```shell
 ./llama-cli \
   --hf-repo "nazimali/mistral-7b-v0.3-instruct-arabic" \
-  --hf-file gguf/Q4_K_M.gguf \
+  --hf-file Q8_0.gguf \
   -p "السلام عليكم، هيا نموء" \
   --conversation
 ```