Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
7cb725b
1 Parent(s): 8b6c85b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -1
README.md CHANGED
@@ -36,12 +36,28 @@ It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQi
36
 
37
  ## Prompt template
38
 
 
 
39
  ```
40
  <|user|>
41
- Your message here!
42
  <|assistant|>
43
  ```
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ## How to easily download and use this model in text-generation-webui
46
 
47
  Please make sure you're using the latest version of text-generation-webui
 
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
62
 
63
  Please make sure you're using the latest version of text-generation-webui