Update README.md
Browse files
README.md
CHANGED
|
@@ -2,20 +2,20 @@
|
|
| 2 |
license: cc-by-sa-4.0
|
| 3 |
---
|
| 4 |
|
| 5 |
-
# SLIM-
|
| 6 |
|
| 7 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 8 |
|
| 9 |
|
| 10 |
-
**slim-
|
| 11 |
|
| 12 |
|
| 13 |
-
[**slim-
|
| 14 |
|
| 15 |
To pull the model via API:
|
| 16 |
|
| 17 |
from huggingface_hub import snapshot_download
|
| 18 |
-
snapshot_download("llmware/slim-
|
| 19 |
|
| 20 |
|
| 21 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
|
@@ -23,14 +23,14 @@ Load in your favorite GGUF inference engine, or try with llmware as follows:
|
|
| 23 |
from llmware.models import ModelCatalog
|
| 24 |
|
| 25 |
# to load the model and make a basic inference
|
| 26 |
-
model = ModelCatalog().load_model("slim-
|
| 27 |
response = model.function_call(text_sample)
|
| 28 |
|
| 29 |
# this one line will download the model and run a series of tests
|
| 30 |
-
ModelCatalog().tool_test_run("slim-
|
| 31 |
|
| 32 |
|
| 33 |
-
Note: please review [**config.json**](https://huggingface.co/llmware/slim-
|
| 34 |
|
| 35 |
|
| 36 |
## Model Card Contact
|
|
|
|
| 2 |
license: cc-by-sa-4.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
# SLIM-SA_NER-TOOL
|
| 6 |
|
| 7 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 8 |
|
| 9 |
|
| 10 |
+
**slim-sa-ner-tool** is a 4_K_M quantized GGUF version of slim-sa-ner, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
|
| 11 |
|
| 12 |
|
| 13 |
+
[**slim-sa-ner**](https://huggingface.co/llmware/slim-sa-ner) is part of the SLIM ("**S**tructured **L**anguage **I**nstruction **M**odel") series, providing a set of small, specialized decoder-based LLMs, fine-tuned for function-calling.
|
| 14 |
|
| 15 |
To pull the model via API:
|
| 16 |
|
| 17 |
from huggingface_hub import snapshot_download
|
| 18 |
+
snapshot_download("llmware/slim-sa-ner-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
|
| 19 |
|
| 20 |
|
| 21 |
Load in your favorite GGUF inference engine, or try with llmware as follows:
|
|
|
|
| 23 |
from llmware.models import ModelCatalog
|
| 24 |
|
| 25 |
# to load the model and make a basic inference
|
| 26 |
+
model = ModelCatalog().load_model("slim-sa-ner-tool")
|
| 27 |
response = model.function_call(text_sample)
|
| 28 |
|
| 29 |
# this one line will download the model and run a series of tests
|
| 30 |
+
ModelCatalog().tool_test_run("slim-sa-ner-tool", verbose=True)
|
| 31 |
|
| 32 |
|
| 33 |
+
Note: please review [**config.json**](https://huggingface.co/llmware/slim-sa-ner-tool/blob/main/config.json) in the repository for prompt wrapping information, details on the model, and full test set.
|
| 34 |
|
| 35 |
|
| 36 |
## Model Card Contact
|