Instructions to use llmware/slim-tags-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmware/slim-tags-tool with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("llmware/slim-tags-tool", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use llmware/slim-tags-tool with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf llmware/slim-tags-tool # Run inference directly in the terminal: llama cli -hf llmware/slim-tags-tool
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf llmware/slim-tags-tool # Run inference directly in the terminal: llama cli -hf llmware/slim-tags-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-tags-tool # Run inference directly in the terminal: ./llama-cli -hf llmware/slim-tags-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-tags-tool # Run inference directly in the terminal: ./build/bin/llama-cli -hf llmware/slim-tags-tool
Use Docker
docker model run hf.co/llmware/slim-tags-tool
- LM Studio
- Jan
- Ollama
How to use llmware/slim-tags-tool with Ollama:
ollama run hf.co/llmware/slim-tags-tool
- Unsloth Desktop
- Docker Model Runner
How to use llmware/slim-tags-tool with Docker Model Runner:
docker model run hf.co/llmware/slim-tags-tool
- Lemonade
How to use llmware/slim-tags-tool with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull llmware/slim-tags-tool
Run and chat with the model
lemonade run user.slim-tags-tool-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Update config.json
Browse files- config.json +6 -6
config.json
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
{
|
| 2 |
-
"model_name": "slim-
|
| 3 |
"quantization": "4Q_K_M GGUF",
|
| 4 |
"model_base": "tiny-llama",
|
| 5 |
"model_type": "llama",
|
| 6 |
"parameters": "1.1 billion",
|
| 7 |
-
"description": "slim-
|
| 8 |
"prompt_wrapper": "human_bot",
|
| 9 |
-
"prompt_format": "<human> {context_passage} <classify>
|
| 10 |
-
"output_format": "{list of
|
| 11 |
"primary_keys": [
|
| 12 |
-
"
|
| 13 |
],
|
| 14 |
"output_values": [
|
| 15 |
-
"list of
|
| 16 |
],
|
| 17 |
"publisher": "llmware",
|
| 18 |
"release_date": "february 2024",
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_name": "slim-tags-tool",
|
| 3 |
"quantization": "4Q_K_M GGUF",
|
| 4 |
"model_base": "tiny-llama",
|
| 5 |
"model_type": "llama",
|
| 6 |
"parameters": "1.1 billion",
|
| 7 |
+
"description": "slim-tags is a function-calling model, fine-tuned to output structured dictionaries",
|
| 8 |
"prompt_wrapper": "human_bot",
|
| 9 |
+
"prompt_format": "<human> {context_passage} <classify> tags </classify>\n<bot>:",
|
| 10 |
+
"output_format": "{list of relevant extractive summary tags in text}",
|
| 11 |
"primary_keys": [
|
| 12 |
+
"tags"
|
| 13 |
],
|
| 14 |
"output_values": [
|
| 15 |
+
"list of extracted tags"
|
| 16 |
],
|
| 17 |
"publisher": "llmware",
|
| 18 |
"release_date": "february 2024",
|