Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ license: apache-2.0
|
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
|
10 |
-
**slim-sql-tool** is a 4_K_M quantized GGUF version of slim-
|
11 |
|
12 |
[**slim-sql**](https://huggingface.co/llmware/slim-sql-1b-v0) 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.
|
13 |
|
@@ -21,15 +21,8 @@ Load in your favorite GGUF inference engine, or try with llmware as follows:
|
|
21 |
|
22 |
from llmware.models import ModelCatalog
|
23 |
|
24 |
-
# to load the model and make a basic inference
|
25 |
-
model = ModelCatalog().load_model("slim-sql-tool")
|
26 |
-
|
27 |
-
# sql_query_prompt is concatenation of sql_table_schema and a natural language query
|
28 |
-
# see config.json script for example
|
29 |
-
|
30 |
-
response = model.function_call(sql_query_prompt)
|
31 |
-
|
32 |
# this one line will download the model and run a series of tests
|
|
|
33 |
ModelCatalog().tool_test_run("slim-sql-tool", verbose=True)
|
34 |
|
35 |
|
|
|
7 |
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
|
9 |
|
10 |
+
**slim-sql-tool** is a 4_K_M quantized GGUF version of slim-sql-1b-v0, providing a small, fast inference implementation, optimized for multi-model concurrent deployment.
|
11 |
|
12 |
[**slim-sql**](https://huggingface.co/llmware/slim-sql-1b-v0) 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.
|
13 |
|
|
|
21 |
|
22 |
from llmware.models import ModelCatalog
|
23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
# this one line will download the model and run a series of tests
|
25 |
+
# includes two sample table schema - go to llmware github repo for end-to-end example
|
26 |
ModelCatalog().tool_test_run("slim-sql-tool", verbose=True)
|
27 |
|
28 |
|