Update README.md

README.md

@@ -6,7 +6,19 @@ base_model:
 - deepseek-ai/DeepSeek-R1
 pipeline_tag: text-generation
 tags:
-- deepseek_v3
+- deepseek-r1
 - gguf-connector
 ---
 
+# GGUF quantized version of **DeepSeek-R1**
+
+### review
+- fixed the error loading message: "unknown pre-tokenizer type: deepseek-r1-qwen"
+- working with llama architecture
+
+### run the model
+use any gguf connector to interact with gguf file(s), i.e., [connector](https://pypi.org/project/gguf-connector/)
+
+### reference
+- base model: deepseek-ai/[DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)
+- tool used for quantization: [cutter](https://pypi.org/project/gguf-cutter)