Update README.md
Browse files
README.md
CHANGED
|
@@ -6,20 +6,20 @@ license: apache-2.0
|
|
| 6 |
|
| 7 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 8 |
|
| 9 |
-
**slim-
|
| 10 |
|
| 11 |
-
slim-
|
| 12 |
|
| 13 |
Load in your favorite GGUF inference engine (see details in config.json to set up the prompt template), or try with llmware as follows:
|
| 14 |
|
| 15 |
from llmware.models import ModelCatalog
|
| 16 |
|
| 17 |
# to load the model and make a basic inference
|
| 18 |
-
|
| 19 |
-
response =
|
| 20 |
|
| 21 |
# this one line will download the model and run a series of tests
|
| 22 |
-
ModelCatalog().test_run("slim-
|
| 23 |
|
| 24 |
|
| 25 |
Slim models can also be loaded even more simply as part of a multi-model, multi-step LLMfx calls:
|
|
@@ -27,8 +27,8 @@ Slim models can also be loaded even more simply as part of a multi-model, multi-
|
|
| 27 |
from llmware.agents import LLMfx
|
| 28 |
|
| 29 |
llm_fx = LLMfx()
|
| 30 |
-
llm_fx.load_tool("
|
| 31 |
-
response = llm_fx.
|
| 32 |
|
| 33 |
|
| 34 |
### Model Description
|
|
@@ -39,7 +39,7 @@ Slim models can also be loaded even more simply as part of a multi-model, multi-
|
|
| 39 |
- **Model type:** GGUF
|
| 40 |
- **Language(s) (NLP):** English
|
| 41 |
- **License:** Apache 2.0
|
| 42 |
-
- **Quantized from model:** llmware/slim-
|
| 43 |
|
| 44 |
## Uses
|
| 45 |
|
|
|
|
| 6 |
|
| 7 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 8 |
|
| 9 |
+
**slim-sql-tool** is part of the SLIM ("Structured Language Instruction Model") model series, providing a set of small, specialized decoder-based LLMs, fine-tuned for function-calling.
|
| 10 |
|
| 11 |
+
slim-sql-tool is a 4_K_M quantized GGUF version of slim-sql, providing a small, fast inference implementation.
|
| 12 |
|
| 13 |
Load in your favorite GGUF inference engine (see details in config.json to set up the prompt template), or try with llmware as follows:
|
| 14 |
|
| 15 |
from llmware.models import ModelCatalog
|
| 16 |
|
| 17 |
# to load the model and make a basic inference
|
| 18 |
+
sql_tool = ModelCatalog().load_model("slim-sql-tool")
|
| 19 |
+
response = sql_tool.function_call(text_sample)
|
| 20 |
|
| 21 |
# this one line will download the model and run a series of tests
|
| 22 |
+
ModelCatalog().test_run("slim-sql-tool", verbose=True)
|
| 23 |
|
| 24 |
|
| 25 |
Slim models can also be loaded even more simply as part of a multi-model, multi-step LLMfx calls:
|
|
|
|
| 27 |
from llmware.agents import LLMfx
|
| 28 |
|
| 29 |
llm_fx = LLMfx()
|
| 30 |
+
llm_fx.load_tool("sql")
|
| 31 |
+
response = llm_fx.sql(text)
|
| 32 |
|
| 33 |
|
| 34 |
### Model Description
|
|
|
|
| 39 |
- **Model type:** GGUF
|
| 40 |
- **Language(s) (NLP):** English
|
| 41 |
- **License:** Apache 2.0
|
| 42 |
+
- **Quantized from model:** llmware/slim-sql (finetuned tiny llama)
|
| 43 |
|
| 44 |
## Uses
|
| 45 |
|