doberst commited on
Commit
9ff7d85
1 Parent(s): b9675aa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -3,12 +3,12 @@ license: apache-2.0
3
  inference: false
4
  ---
5
 
6
- # SLIM-EXTRACT-PHI-3-TOOL
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
 
11
- **slim-extract-phi-3-tool** is a function-calling extraction, finetuned on top of phi-3-mini, and then then 4_K_M quantized with GGUF, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
12
 
13
  This model has been fine-tuned to implement a general-purpose extraction function that takes a custom key as input parameter, and generates a python dictionary consisting of that custom key with the value consisting of a list of the values associated with that key in the text.
14
 
@@ -20,7 +20,7 @@ The intent of SLIMs is to forge a middle-ground between traditional encoder-base
20
  To pull the model via API:
21
 
22
  from huggingface_hub import snapshot_download
23
- snapshot_download("llmware/slim-extract-phi-3-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
24
 
25
 
26
  Load in your favorite GGUF inference engine, or try with llmware as follows:
@@ -28,14 +28,14 @@ Load in your favorite GGUF inference engine, or try with llmware as follows:
28
  from llmware.models import ModelCatalog
29
 
30
  # to load the model and make a basic inference
31
- model = ModelCatalog().load_model("slim-extract-phi-3-tool")
32
  response = model.function_call(text_sample)
33
 
34
  # this one line will download the model and run a series of tests
35
- ModelCatalog().tool_test_run("slim-extract-phi-3-tool", verbose=True)
36
 
37
 
38
- Note: please review [**config.json**](https://huggingface.co/llmware/slim-extract-phi-3-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
39
 
40
 
41
  ## Model Card Contact
 
3
  inference: false
4
  ---
5
 
6
+ # SLIM-EXTRACT-PHI-3-GGUF
7
 
8
  <!-- Provide a quick summary of what the model is/does. -->
9
 
10
 
11
+ **slim-extract-phi-3-gguf** is a function-calling extraction, finetuned on top of phi-3-mini, and then then 4_K_M quantized with GGUF, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
12
 
13
  This model has been fine-tuned to implement a general-purpose extraction function that takes a custom key as input parameter, and generates a python dictionary consisting of that custom key with the value consisting of a list of the values associated with that key in the text.
14
 
 
20
  To pull the model via API:
21
 
22
  from huggingface_hub import snapshot_download
23
+ snapshot_download("llmware/slim-extract-phi-3-gguf", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
24
 
25
 
26
  Load in your favorite GGUF inference engine, or try with llmware as follows:
 
28
  from llmware.models import ModelCatalog
29
 
30
  # to load the model and make a basic inference
31
+ model = ModelCatalog().load_model("slim-extract-phi-3-gguf")
32
  response = model.function_call(text_sample)
33
 
34
  # this one line will download the model and run a series of tests
35
+ ModelCatalog().tool_test_run("slim-extract-phi-3-gguf", verbose=True)
36
 
37
 
38
+ Note: please review [**config.json**](https://huggingface.co/llmware/slim-extract-phi-3-gguf/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
39
 
40
 
41
  ## Model Card Contact