Instructions to use llmware/slim-sql-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-sql-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/slim-sql-tool", dtype="auto")

llama-cpp-python

How to use llmware/slim-sql-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/slim-sql-tool",
	filename="slim-sql.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use llmware/slim-sql-tool with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/slim-sql-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/slim-sql-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/slim-sql-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/slim-sql-tool

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf llmware/slim-sql-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/slim-sql-tool

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf llmware/slim-sql-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/slim-sql-tool

Use Docker

docker model run hf.co/llmware/slim-sql-tool

LM Studio
Jan
Ollama
How to use llmware/slim-sql-tool with Ollama:
```
ollama run hf.co/llmware/slim-sql-tool
```

Unsloth Studio

How to use llmware/slim-sql-tool with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for llmware/slim-sql-tool to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for llmware/slim-sql-tool to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmware/slim-sql-tool to start chatting

Docker Model Runner
How to use llmware/slim-sql-tool with Docker Model Runner:
```
docker model run hf.co/llmware/slim-sql-tool
```

Lemonade

How to use llmware/slim-sql-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/slim-sql-tool

Run and chat with the model

lemonade run user.slim-sql-tool-{{QUANT_TAG}}

List all available models

lemonade list

doberst commited on Jan 29, 2024

Commit

67d51f0

verified ·

1 Parent(s): 1ce4968

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -6,20 +6,20 @@ license: apache-2.0
 <!-- Provide a quick summary of what the model is/does. -->
-**slim-ner-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.
-slim-ner-tool is a 4_K_M quantized GGUF version of slim-ner, providing a small, fast inference implementation.
 Load in your favorite GGUF inference engine (see details in config.json to set up the prompt template), or try with llmware as follows:
     from llmware.models import ModelCatalog
     # to load the model and make a basic inference
-    ner_tool = ModelCatalog().load_model("slim-ner-tool")
-    response = ner_tool.function_call(text_sample)
     # this one line will download the model and run a series of tests
-    ModelCatalog().test_run("slim-ner-tool", verbose=True)
 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-
     from llmware.agents import LLMfx
     llm_fx = LLMfx()
-    llm_fx.load_tool("ner")
-    response = llm_fx.named_entity_extraction(text)
 ### Model Description
@@ -39,7 +39,7 @@ Slim models can also be loaded even more simply as part of a multi-model, multi-
 - **Model type:** GGUF
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
-- **Quantized from model:** llmware/slim-sentiment (finetuned tiny llama)
 ## Uses

 <!-- Provide a quick summary of what the model is/does. -->
+**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.
+slim-sql-tool is a 4_K_M quantized GGUF version of slim-sql, providing a small, fast inference implementation.
 Load in your favorite GGUF inference engine (see details in config.json to set up the prompt template), or try with llmware as follows:
     from llmware.models import ModelCatalog
     # to load the model and make a basic inference
+    sql_tool = ModelCatalog().load_model("slim-sql-tool")
+    response = sql_tool.function_call(text_sample)
     # this one line will download the model and run a series of tests
+    ModelCatalog().test_run("slim-sql-tool", verbose=True)
 Slim models can also be loaded even more simply as part of a multi-model, multi-step LLMfx calls:
     from llmware.agents import LLMfx
     llm_fx = LLMfx()
+    llm_fx.load_tool("sql")
+    response = llm_fx.sql(text)
 ### Model Description
 - **Model type:** GGUF
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
+- **Quantized from model:** llmware/slim-sql (finetuned tiny llama)
 ## Uses