Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
b6e7a3d
1 Parent(s): 7d4e98a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -10
README.md CHANGED
@@ -36,26 +36,21 @@ It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQi
36
 
37
  ## Prompt template
38
 
39
- According to the original model's README, the following template should be used:
40
 
41
  ```
42
  <|user|>
43
  prompt goes here
44
  <|assistant|>
45
- ```
46
-
47
- However in my own testing, this seems to return no response at all. But I do get good responses using:
48
 
49
  ```
50
- ### Instruction: prompt goes here
51
- ### Response:
52
- ```
53
 
54
- and
 
 
55
 
56
  ```
57
- USER: prompt goes here
58
- ASSISTANT:
59
  ```
60
 
61
  ## How to easily download and use this model in text-generation-webui
 
36
 
37
  ## Prompt template
38
 
39
+ The following template should be used:
40
 
41
  ```
42
  <|user|>
43
  prompt goes here
44
  <|assistant|>
 
 
 
45
 
46
  ```
 
 
 
47
 
48
+ **Note**: There should be a newline after `<|assistant|>`. This appears to be very important for getting this model to respond correctly.
49
+
50
+ In other words, the prompt is:
51
 
52
  ```
53
+ <|user|>\nprompt goes here\n<|assistant|>\n
 
54
  ```
55
 
56
  ## How to easily download and use this model in text-generation-webui