Instructions to use llmware/slim-qa-gen-phi-3-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmware/slim-qa-gen-phi-3-tool with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("llmware/slim-qa-gen-phi-3-tool", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use llmware/slim-qa-gen-phi-3-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-qa-gen-phi-3-tool # Run inference directly in the terminal: llama cli -hf llmware/slim-qa-gen-phi-3-tool
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf llmware/slim-qa-gen-phi-3-tool # Run inference directly in the terminal: llama cli -hf llmware/slim-qa-gen-phi-3-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-qa-gen-phi-3-tool # Run inference directly in the terminal: ./llama-cli -hf llmware/slim-qa-gen-phi-3-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-qa-gen-phi-3-tool # Run inference directly in the terminal: ./build/bin/llama-cli -hf llmware/slim-qa-gen-phi-3-tool
Use Docker
docker model run hf.co/llmware/slim-qa-gen-phi-3-tool
- LM Studio
- Jan
- Ollama
How to use llmware/slim-qa-gen-phi-3-tool with Ollama:
ollama run hf.co/llmware/slim-qa-gen-phi-3-tool
- Unsloth Desktop
- Docker Model Runner
How to use llmware/slim-qa-gen-phi-3-tool with Docker Model Runner:
docker model run hf.co/llmware/slim-qa-gen-phi-3-tool
- Lemonade
How to use llmware/slim-qa-gen-phi-3-tool with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull llmware/slim-qa-gen-phi-3-tool
Run and chat with the model
lemonade run user.slim-qa-gen-phi-3-tool-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -4,13 +4,13 @@
|
|
| 4 |
"quantization": "4Q_K_M GGUF",
|
| 5 |
"model_base": "microsoft/Phi-3-mini-4k-instruct",
|
| 6 |
"model_type": "phi3",
|
| 7 |
-
"tokenizer": "llmware/slim-qa-gen-phi-3
|
| 8 |
"tokenizer_local": "tokenizer_phi3.json",
|
| 9 |
"parameters": "3.8 billion",
|
| 10 |
"description": "slim-qa-gen-phi-3 is a function-calling model, fine-tuned to output structured dictionaries",
|
| 11 |
"prompt_wrapper": "human_bot",
|
| 12 |
-
"prompt_format": "<human> {context_passage} <generate> {
|
| 13 |
-
"output_format": "{'
|
| 14 |
"primary_keys": ["question, answer", "boolean", "multiple choice"],
|
| 15 |
"output_values": ["question", "answer"],
|
| 16 |
"publisher": "llmware",
|
|
|
|
| 4 |
"quantization": "4Q_K_M GGUF",
|
| 5 |
"model_base": "microsoft/Phi-3-mini-4k-instruct",
|
| 6 |
"model_type": "phi3",
|
| 7 |
+
"tokenizer": "llmware/slim-qa-gen-phi-3",
|
| 8 |
"tokenizer_local": "tokenizer_phi3.json",
|
| 9 |
"parameters": "3.8 billion",
|
| 10 |
"description": "slim-qa-gen-phi-3 is a function-calling model, fine-tuned to output structured dictionaries",
|
| 11 |
"prompt_wrapper": "human_bot",
|
| 12 |
+
"prompt_format": "<human> {context_passage} <generate> { one of primary_key } </generate>\n<bot>:",
|
| 13 |
+
"output_format": "{'question': ['custom generated question from passage'], 'answer': ['answer to question'] }",
|
| 14 |
"primary_keys": ["question, answer", "boolean", "multiple choice"],
|
| 15 |
"output_values": ["question", "answer"],
|
| 16 |
"publisher": "llmware",
|