apepkuss79 commited on
Commit
0d873cd
1 Parent(s): 5798516

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -31,6 +31,10 @@ quantized_by: Second State Inc.
31
 
32
  prompt template: `chatml`
33
 
 
 
 
 
34
  **Context size:**
35
 
36
  chat_ctx_size: `4096`
@@ -60,4 +64,4 @@ chat_ctx_size: `4096`
60
  | [Yi-1.5-9B-Chat-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended |
61
  | [Yi-1.5-9B-Chat-f16.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-f16.gguf) | f16 | 16 | 17.7 GB| |
62
 
63
- *Quantized with llama.cpp b2824*
 
31
 
32
  prompt template: `chatml`
33
 
34
+ **Reverse prompt**
35
+
36
+ reverse prompt: `<|im_end|>`
37
+
38
  **Context size:**
39
 
40
  chat_ctx_size: `4096`
 
64
  | [Yi-1.5-9B-Chat-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended |
65
  | [Yi-1.5-9B-Chat-f16.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-f16.gguf) | f16 | 16 | 17.7 GB| |
66
 
67
+ *Quantized with llama.cpp b3135*