Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,8 @@ pipeline_tag: text-generation
|
|
| 23 |
|
| 24 |
## Llamacpp iMatrix Quantizations of dolphin-2.9-llama3-8b
|
| 25 |
|
|
|
|
|
|
|
| 26 |
This model has the <|eot_id|> token set to not-special, which seems to work better with current inference engines.
|
| 27 |
|
| 28 |
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.
|
|
|
|
| 23 |
|
| 24 |
## Llamacpp iMatrix Quantizations of dolphin-2.9-llama3-8b
|
| 25 |
|
| 26 |
+
## This model has been deprecated in favour of the requanted version with tokenizer fixes here: https://huggingface.co/bartowski/dolphin-2.9-llama3-8b-GGUF
|
| 27 |
+
|
| 28 |
This model has the <|eot_id|> token set to not-special, which seems to work better with current inference engines.
|
| 29 |
|
| 30 |
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.
|