doberst commited on
Commit
22d474f
1 Parent(s): 2c2c967

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -7,13 +7,13 @@ inference: false
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
- **slim-boolean** is an experimental model designed to implement a boolean function call using a 2.7B parameter specialized model. As an input, the model takes a context passage, a yes-no question, and an optional (explain) parameter, and as output, the model generates a python dictionary with two keys - 'answer' which contains the 'yes/no' classification, and 'explain' which provides a text snippet from the passage that was the basis for the classification, e.g.:
11
 
12
  &nbsp;&nbsp;&nbsp;&nbsp;`{'answer': ['yes'], 'explanation': ['the results exceeded expectations by 3%'] }`
13
 
14
  This model is fine-tuned on top of [**llmware/bling-stable-lm-3b-4e1t-v0**](https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0), which in turn, is a fine-tune of stabilityai/stablelm-3b-4elt.
15
 
16
- For fast inference, we would recommend using the'quantized tool' version, e.g., [**'slim-boolean-tool'**](https://huggingface.co/llmware/slim-sa-ner-3b-tool).
17
 
18
 
19
  ## Prompt format:
 
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
+ **slim-boolean** is an experimental model designed to implement a boolean question answering function call using a 2.7B parameter specialized model. As an input, the model takes a context passage, a yes-no question, and an optional (explain) parameter, and as output, the model generates a python dictionary with two keys - 'answer' which contains the 'yes/no' classification, and 'explain' which provides a text snippet from the passage that was the basis for the classification, e.g.:
11
 
12
  &nbsp;&nbsp;&nbsp;&nbsp;`{'answer': ['yes'], 'explanation': ['the results exceeded expectations by 3%'] }`
13
 
14
  This model is fine-tuned on top of [**llmware/bling-stable-lm-3b-4e1t-v0**](https://huggingface.co/llmware/bling-stable-lm-3b-4e1t-v0), which in turn, is a fine-tune of stabilityai/stablelm-3b-4elt.
15
 
16
+ For fast inference, we would recommend using the'quantized tool' version, e.g., [**'slim-boolean-tool'**](https://huggingface.co/llmware/slim-boolean-tool).
17
 
18
 
19
  ## Prompt format: