apepkuss79 commited on
Commit
383b00d
1 Parent(s): c555685

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -43,6 +43,8 @@ quantized_by: Second State Inc.
43
  <|im_start|>assistant
44
  ```
45
 
 
 
46
  - Context size: `16384`
47
 
48
  - Run as LlamaEdge service
@@ -51,6 +53,7 @@ quantized_by: Second State Inc.
51
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
52
  llama-api-server.wasm \
53
  --prompt-template chatml \
 
54
  --ctx-size 16384 \
55
  --model-name Yi-1.5-34B-Chat-16K
56
  ```
@@ -61,6 +64,7 @@ quantized_by: Second State Inc.
61
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
62
  llama-chat.wasm \
63
  --prompt-template chatml \
 
64
  --ctx-size 16384
65
  ```
66
 
@@ -84,4 +88,4 @@ quantized_by: Second State Inc.
84
  | [Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf) | f16 | 16 | 32.1 GB| |
85
  | [Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf) | f16 | 16 | 4.48 GB| |
86
 
87
- *Quantized with llama.cpp b2824*
 
43
  <|im_start|>assistant
44
  ```
45
 
46
+ - Reverse prompt: `<|im_end|>`
47
+
48
  - Context size: `16384`
49
 
50
  - Run as LlamaEdge service
 
53
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
54
  llama-api-server.wasm \
55
  --prompt-template chatml \
56
+ --reverse-prompt "<|im_end|>" \
57
  --ctx-size 16384 \
58
  --model-name Yi-1.5-34B-Chat-16K
59
  ```
 
64
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
65
  llama-chat.wasm \
66
  --prompt-template chatml \
67
+ --reverse-prompt "<|im_end|>" \
68
  --ctx-size 16384
69
  ```
70
 
 
88
  | [Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf) | f16 | 16 | 32.1 GB| |
89
  | [Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf) | f16 | 16 | 4.48 GB| |
90
 
91
+ *Quantized with llama.cpp b3135*