Update README.md
Browse files
README.md
CHANGED
@@ -190,7 +190,9 @@ quantized_by: bartowski
|
|
190 |
|
191 |
## Llamacpp Quantizations of Meta-Llama-3-8B-Instruct
|
192 |
|
193 |
-
|
|
|
|
|
194 |
|
195 |
Original model: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
196 |
|
|
|
190 |
|
191 |
## Llamacpp Quantizations of Meta-Llama-3-8B-Instruct
|
192 |
|
193 |
+
This model has the <|eot_id|> token set to not-special, which seems to work better with current inference engines.
|
194 |
+
|
195 |
+
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> fork from pcuenca <a href="https://github.com/pcuenca/llama.cpp/tree/llama3-conversion">llama3-conversion</a> for quantization.
|
196 |
|
197 |
Original model: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
198 |
|