Update README.md
Browse files
README.md
CHANGED
@@ -190,6 +190,8 @@ quantized_by: bartowski
|
|
190 |
|
191 |
## Llamacpp iMatrix 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.
|
|
|
190 |
|
191 |
## Llamacpp iMatrix Quantizations of Meta-Llama-3-8B-Instruct
|
192 |
|
193 |
+
<b>Now that the official release supporting Llama 3 is out [here](https://github.com/ggerganov/llama.cpp/releases/tag/b2710), this will be tagged "-old" and new quants will be made with no changes to configuration</b>
|
194 |
+
|
195 |
This model has the <|eot_id|> token set to not-special, which seems to work better with current inference engines.
|
196 |
|
197 |
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.
|