Update README.md

README.md

@@ -22,8 +22,18 @@ Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language
 * Stable support of 32K context length for models of all sizes
 * No need of `trust_remote_code`.
 
-For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). In this repo, we provide the `q5_k_m` quantized model in the GGUF format.
-<br>
+For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). 
+In this repo, we provide quantized models in the GGUF formats, including `q2_k`, `q3_k_m`, `q4_0`, `q4_k_m`, `q5_0`, `q5_k_m`, `q6_k` and `q8_0`. 
+To demonstrate their model quality, we follow [`llama.cpp`](https://github.com/ggerganov/llama.cpp) to evaluate their perplexity on wiki test set. Results are shown below:
+
+|Size    | fp16    | q8_0    | q6_k    | q5_k_m  | q5_0    | q4_k_m  | q4_0    | q3_k_m  | q2_k    |
+|--------|---------|---------|---------|---------|---------|---------|---------|---------|---------|
+|0.5B    | 34.20   | 34.22   | 34.31   | 33.80   | 34.02   | 34.27   | 36.74   | 38.25   | 62.14   |
+|1.8B    | 15.99   | 15.99   | 15.99   | 16.09   | 16.01   | 16.22   | 16.54   | 17.03   | 19.99   |
+|4B      | 13.20   | 13.21   | 13.28   | 13.24   | 13.27   | 13.61   | 13.44   | 13.67   | 15.65   |
+|7B      | 14.21   | 14.24   | 14.35   | 14.32   | 14.12   | 14.35   | 14.47   | 15.11   | 16.57   |
+|14B     | 10.91   | 10.91   | 10.93   | 10.98   | 10.88   | 10.92   | 10.92   | 11.24   | 12.27   |
+|72B     | 7.97    | 7.99    | 7.99    | 7.99    | 8.01    | 8.00    | 8.01    | 8.06    | 8.63    |
 
 ## Model Details
 Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA and the mixture of SWA and full attention.