Update README.md

README.md

@@ -190,6 +190,20 @@ quantized_by: bartowski
 
 ## Exllama v2 Quantizations of Meta-Llama-3-8B-Instruct
 
+If generation refuses to stop, you can edit tokenizer_config.json.
+
+Replace line 2055:
+
+```
+"eos_token": "<|end_of_text|>",
+```
+
+with:
+
+```
+"eos_token": "<|eot_id|>",
+```
+
 Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
 
 <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>