Text Generation
Transformers
PyTorch
English
llama
sft
Inference Endpoints
text-generation-inference
andreaskoepf commited on
Commit
1e72484
1 Parent(s): 036be44

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -32,10 +32,10 @@ on the best human demonstrations collected at [open-assistant.io](https://open-a
32
 
33
  ## Prompting / Prompt Template
34
 
35
- Due to public demand we changed the prompt-template for this model from custom prompter/assistant tokens to OpenAI's [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) standard prompt format.
36
  We hope that this leads to greater compatibility with chat inference/frontend applications.
37
 
38
- Prompt template:
39
 
40
  ```
41
  """
@@ -64,6 +64,7 @@ For inference we recommend to use the official [Llama2 system message](https://g
64
  ```
65
  <|im_start|>system
66
  You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
 
67
  If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
68
  <|im_end|>
69
  ```
 
32
 
33
  ## Prompting / Prompt Template
34
 
35
+ Due to public demand (see [survey](https://twitter.com/erhartford/status/1682403597525430272)) we changed the prompt-template for this model from custom prompter/assistant tokens to OpenAI's [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) standard prompt format.
36
  We hope that this leads to greater compatibility with chat inference/frontend applications.
37
 
38
+ Prompt dialogue template:
39
 
40
  ```
41
  """
 
64
  ```
65
  <|im_start|>system
66
  You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
67
+
68
  If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
69
  <|im_end|>
70
  ```