DarwinAnim8or commited on
Commit
3ab1f76
·
1 Parent(s): 740c5e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -14,6 +14,8 @@ tags:
14
 
15
  This is a text generation model based on the [OPT-1.3B](https://huggingface.co/facebook/opt-1.3b) model from Meta, trained using the Deepspeed library. The model can generate natural and engaging conversational responses given a user input.
16
 
 
 
17
  ## Training Details
18
 
19
  - The base model is [OPT-1.3B](https://huggingface.co/facebook/opt-1.3b), a decoder-only transformer with 1.3 billion parameters, pre-trained on a large text corpus using the causal language modeling objective.
@@ -39,6 +41,15 @@ generator = pipeline('text-generation', model='DarwinAnim8or/OPT-1.3b-Chat')
39
  generator("Hello, how are you?")
40
  ```
41
 
 
 
 
 
 
 
 
 
 
42
  ## License
43
  This model is licensed under the [OPT-175B license](https://github.com/facebookresearch/metaseq/blob/main/projects/OPT/MODEL_LICENSE.md), which is a non-commercial research license. Please read the full license terms before using this model.
44
 
 
14
 
15
  This is a text generation model based on the [OPT-1.3B](https://huggingface.co/facebook/opt-1.3b) model from Meta, trained using the Deepspeed library. The model can generate natural and engaging conversational responses given a user input.
16
 
17
+ A Demo is [available here](https://huggingface.co/spaces/KoalaAI/OPT-Chat)
18
+
19
  ## Training Details
20
 
21
  - The base model is [OPT-1.3B](https://huggingface.co/facebook/opt-1.3b), a decoder-only transformer with 1.3 billion parameters, pre-trained on a large text corpus using the causal language modeling objective.
 
41
  generator("Hello, how are you?")
42
  ```
43
 
44
+ ### Suggested formatting
45
+ The training data uses the following format:
46
+ ```
47
+ Human: <question>
48
+ Assistant: <answer>
49
+ ```
50
+
51
+ It is recommended to follow the same format as closely as possible for the best results.
52
+
53
  ## License
54
  This model is licensed under the [OPT-175B license](https://github.com/facebookresearch/metaseq/blob/main/projects/OPT/MODEL_LICENSE.md), which is a non-commercial research license. Please read the full license terms before using this model.
55