doberst commited on
Commit
5356583
1 Parent(s): ec0960f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -1,13 +1,14 @@
1
  ---
2
- license: cc-by-sa-4.0
3
- ---
 
4
 
5
- # SLIM-BOOLEAN-TOOL
6
 
7
  <!-- Provide a quick summary of what the model is/does. -->
8
 
9
 
10
- **slim-boolean-tool** is a 4_K_M quantized GGUF version of slim-boolean, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
11
 
12
  This is an experimental model that takes as input a context passage, a yes-no question, and an optional (explain) parameter, and generates a response consisting of a python dictionary with two keys- 'answer' consisting of the 'yes/no' classification, and 'explanation' which provides a text explanation, derived from the source passage that explains the boolean classification assesment. All of the details on the prompt template are provided in the config.json file in this model repo, along with several examples.
13
 
@@ -16,7 +17,7 @@ If you are interested in fine-tuning this model for a specific domain, please se
16
  To pull the model via API:
17
 
18
  from huggingface_hub import snapshot_download
19
- snapshot_download("llmware/slim-boolean-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
20
 
21
 
22
  Load in your favorite GGUF inference engine, or try with llmware as follows:
@@ -24,14 +25,14 @@ Load in your favorite GGUF inference engine, or try with llmware as follows:
24
  from llmware.models import ModelCatalog
25
 
26
  # to load the model and make a basic inference
27
- model = ModelCatalog().load_model("slim-boolean-tool")
28
  response = model.function_call(text_sample)
29
 
30
  # this one line will download the model and run a series of tests
31
- ModelCatalog().tool_test_run("slim-boolean-tool", verbose=True)
32
 
33
 
34
- Note: please review [**config.json**](https://huggingface.co/llmware/slim-boolean-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
35
 
36
 
37
  ## Model Card Contact
 
1
  ---
2
+ license: apache-2.0
3
+ inference: false
4
+ ---
5
 
6
+ # SLIM-BOOLEAN-PHI-3-GGUF
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
 
11
+ **slim-boolean-phi-3-gguf** is a 4_K_M quantized GGUF version of slim-boolean, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
12
 
13
  This is an experimental model that takes as input a context passage, a yes-no question, and an optional (explain) parameter, and generates a response consisting of a python dictionary with two keys- 'answer' consisting of the 'yes/no' classification, and 'explanation' which provides a text explanation, derived from the source passage that explains the boolean classification assesment. All of the details on the prompt template are provided in the config.json file in this model repo, along with several examples.
14
 
 
17
  To pull the model via API:
18
 
19
  from huggingface_hub import snapshot_download
20
+ snapshot_download("llmware/slim-boolean-phi-3-gguf", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
21
 
22
 
23
  Load in your favorite GGUF inference engine, or try with llmware as follows:
 
25
  from llmware.models import ModelCatalog
26
 
27
  # to load the model and make a basic inference
28
+ model = ModelCatalog().load_model("slim-boolean-phi-3-gguf")
29
  response = model.function_call(text_sample)
30
 
31
  # this one line will download the model and run a series of tests
32
+ ModelCatalog().tool_test_run("slim-boolean-phi-3-gguf", verbose=True)
33
 
34
 
35
+ Note: please review [**config.json**](https://huggingface.co/llmware/slim-boolean-phi-3-gguf/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
36
 
37
 
38
  ## Model Card Contact