apepkuss79
commited on
Commit
•
add6174
1
Parent(s):
5000ece
Update README.md
Browse files
README.md
CHANGED
@@ -25,6 +25,10 @@ quantized_by: Second State Inc.
|
|
25 |
|
26 |
prompt template: `chatml`
|
27 |
|
|
|
|
|
|
|
|
|
28 |
**Context size**
|
29 |
|
30 |
chat_ctx_size: `16384`
|
@@ -53,4 +57,4 @@ chat_ctx_size: `16384`
|
|
53 |
| [Yi-1.5-9B-Chat-16K-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended |
|
54 |
| [Yi-1.5-9B-Chat-16K-f16.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-f16.gguf) | f16 | 16 | 17.7 GB| |
|
55 |
|
56 |
-
*Quantized with llama.cpp
|
|
|
25 |
|
26 |
prompt template: `chatml`
|
27 |
|
28 |
+
**Reverse prompt**
|
29 |
+
|
30 |
+
reverse prompt: `<|im_end|>`
|
31 |
+
|
32 |
**Context size**
|
33 |
|
34 |
chat_ctx_size: `16384`
|
|
|
57 |
| [Yi-1.5-9B-Chat-16K-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended |
|
58 |
| [Yi-1.5-9B-Chat-16K-f16.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-16K-GGUF/blob/main/Yi-1.5-9B-Chat-16K-f16.gguf) | f16 | 16 | 17.7 GB| |
|
59 |
|
60 |
+
*Quantized with llama.cpp b3135*
|