Update README.md
Browse files
README.md
CHANGED
|
@@ -188,6 +188,10 @@ extra_gated_button_content: Submit
|
|
| 188 |
quantized_by: bartowski
|
| 189 |
---
|
| 190 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 191 |
## Llamacpp Quantizations of Meta-Llama-3-8B-Instruct
|
| 192 |
|
| 193 |
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.
|
|
|
|
| 188 |
quantized_by: bartowski
|
| 189 |
---
|
| 190 |
|
| 191 |
+
## This model may get strange behaviour due to several of its tokens being labelled as "special", and so most tools will not properly detect them. This is most noticeable with the stop token.
|
| 192 |
+
|
| 193 |
+
A new upload is on the way and will be replacing this one.
|
| 194 |
+
|
| 195 |
## Llamacpp Quantizations of Meta-Llama-3-8B-Instruct
|
| 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.
|