Update README.md
Browse files
README.md
CHANGED
@@ -1,13 +1,14 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
3 |
---
|
4 |
|
5 |
-
# SLIM-EXTRACT-
|
6 |
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
|
10 |
-
**slim-extract-
|
11 |
|
12 |
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.
|
13 |
|
@@ -19,7 +20,7 @@ The intent of SLIMs is to forge a middle-ground between traditional encoder-base
|
|
19 |
To pull the model via API:
|
20 |
|
21 |
from huggingface_hub import snapshot_download
|
22 |
-
snapshot_download("llmware/slim-extract-
|
23 |
|
24 |
|
25 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
@@ -27,14 +28,14 @@ Load in your favorite GGUF inference engine, or try with llmware as follows:
|
|
27 |
from llmware.models import ModelCatalog
|
28 |
|
29 |
# to load the model and make a basic inference
|
30 |
-
model = ModelCatalog().load_model("slim-extract-
|
31 |
response = model.function_call(text_sample)
|
32 |
|
33 |
# this one line will download the model and run a series of tests
|
34 |
-
ModelCatalog().tool_test_run("slim-extract-
|
35 |
|
36 |
|
37 |
-
Note: please review [**config.json**](https://huggingface.co/llmware/slim-extract-
|
38 |
|
39 |
|
40 |
## Model Card Contact
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
inference: false
|
4 |
---
|
5 |
|
6 |
+
# SLIM-EXTRACT-QWEN-1.5B-GGUF
|
7 |
|
8 |
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
10 |
|
11 |
+
**slim-extract-qwen-1.5b-gguf** is a 4_K_M quantized GGUF version of slim-extract, 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-qwen-1.5b-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-qwen-1.5b-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-qwen-1.5b-gguf", verbose=True)
|
36 |
|
37 |
|
38 |
+
Note: please review [**config.json**](https://huggingface.co/llmware/slim-extract-qwen-1.5b-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
|