bartowski commited on
Commit
0c59b80
1 Parent(s): 622826c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -15,7 +15,9 @@ pipeline_tag: text-generation
15
 
16
  ## Llamacpp iMatrix Quantizations of llama-3-neural-chat-v1-8b
17
 
18
- Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/experimental">experimental</a> for quantization.
 
 
19
 
20
  Original model: https://huggingface.co/Locutusque/llama-3-neural-chat-v1-8b
21
 
 
15
 
16
  ## Llamacpp iMatrix Quantizations of llama-3-neural-chat-v1-8b
17
 
18
+ This model has the <|eot_id|> token set to not-special, which seems to work better with current inference engines.
19
+
20
+ 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.
21
 
22
  Original model: https://huggingface.co/Locutusque/llama-3-neural-chat-v1-8b
23