Update README.md

README.md

@@ -3,16 +3,23 @@ license: apache-2.0
 datasets:
 - wikimedia/wikipedia
 language:
-- ch
 - zh
 - en
 base_model:
 - meta-llama/Llama-3.2-3B
 ---
+continued pretraining with wiki-zh
+dataset = load_dataset("wikimedia/wikipedia", "20231101.zh", split = "train",)
 
-**this gguf is for ollama**
+and sft with FreedomIntelligence/alpaca-gpt4-zh
 
-**you can make the ollama model with modelfile**
+using unsloth 
+
+use the model-unsloth.gguf file or model-unsloth-Q4_K_M.gguf file in llama.cpp or a UI based system like GPT4All. 
+
+
+
+aslo you can make the ollama model with modelfile
 
 template
 ```
@@ -41,4 +48,4 @@ template
 {{ .Response }}<|end_of_text|>
 ```
 
-**or just use ollama run lastmass/llama3.2-chinese**
+or just use ollama run lastmass/llama3.2-chinese