Update README.md

README.md

@@ -188,6 +188,8 @@ extra_gated_description: The information you provide will be collected, stored,
 extra_gated_button_content: Submit
 ---
 
+<br><hr>
+
 # Llama.cpp imatrix quantizations of meta-llama/Meta-Llama-3.1-8B-Instruct
 
 Using llama.cpp commit [b5e9546](https://github.com/ggerganov/llama.cpp/commit/b5e95468b1676e1e5c9d80d1eeeb26f542a38f42) for quantization, featuring llama 3.1 rope scaling factors. This fixes low-quality issues when using 8-128k context lengths.
@@ -196,6 +198,12 @@ Original model: [https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct](h
 
 All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
 
+Note: There is a new [chat template](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/discussions/53) coming to fix tool use, which has not been merged yet. This repo uses the current chat template, which doesn't support tool use. If you need this feature, you need to [edit the metadata](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/scripts/gguf_set_metadata.py) of the model yourself.
+
+<hr><br>
+
+# Original model card:
+
 ## Model Information
 
 The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.
@@ -292,7 +300,7 @@ Where to send questions or comments about the model Instructions on how to provi
 
 **Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.1 Community License. Use in languages beyond those explicitly referenced as supported in this model card**.
 
-**<span style="text-decoration:underline;">Note</span>: Llama 3.1 has been trained on a broader collection of languages than the 8 supported languages. Developers may fine-tune Llama 3.1 models for languages beyond the 8 supported languages provided they comply with the Llama 3.1 Community License and the Acceptable Use Policy and in such cases are responsible for ensuring that any uses of Llama 3.1 in additional languages is done in a safe and responsible manner.
+**Note**: Llama 3.1 has been trained on a broader collection of languages than the 8 supported languages. Developers may fine-tune Llama 3.1 models for languages beyond the 8 supported languages provided they comply with the Llama 3.1 Community License and the Acceptable Use Policy and in such cases are responsible for ensuring that any uses of Llama 3.1 in additional languages is done in a safe and responsible manner.
 
 ## How to use