Instructions to use llmware/slim-q-gen-phi-3-tool with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmware/slim-q-gen-phi-3-tool with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmware/slim-q-gen-phi-3-tool", dtype="auto")

llama-cpp-python

How to use llmware/slim-q-gen-phi-3-tool with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmware/slim-q-gen-phi-3-tool",
	filename="q_gen.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use llmware/slim-q-gen-phi-3-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-q-gen-phi-3-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/slim-q-gen-phi-3-tool

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmware/slim-q-gen-phi-3-tool
# Run inference directly in the terminal:
llama-cli -hf llmware/slim-q-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-q-gen-phi-3-tool
# Run inference directly in the terminal:
./llama-cli -hf llmware/slim-q-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-q-gen-phi-3-tool
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmware/slim-q-gen-phi-3-tool

Use Docker

docker model run hf.co/llmware/slim-q-gen-phi-3-tool

LM Studio
Jan
Ollama
How to use llmware/slim-q-gen-phi-3-tool with Ollama:
```
ollama run hf.co/llmware/slim-q-gen-phi-3-tool
```

Unsloth Studio

How to use llmware/slim-q-gen-phi-3-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-q-gen-phi-3-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-q-gen-phi-3-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-q-gen-phi-3-tool to start chatting

Docker Model Runner
How to use llmware/slim-q-gen-phi-3-tool with Docker Model Runner:
```
docker model run hf.co/llmware/slim-q-gen-phi-3-tool
```

Lemonade

How to use llmware/slim-q-gen-phi-3-tool with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmware/slim-q-gen-phi-3-tool

Run and chat with the model

lemonade run user.slim-q-gen-phi-3-tool-{{QUANT_TAG}}

List all available models

lemonade list

doberst commited on May 27, 2024

Commit

a4cda8b

verified ·

1 Parent(s): 2442e03

Update config.json

Browse files

Files changed (1) hide show

config.json +13 -12

config.json CHANGED Viewed

@@ -1,19 +1,20 @@
 {
- "model_name": "slim-extract-tool",
- "model_ft_base": "slim-extract",
  "quantization": "4Q_K_M GGUF",
- "model_base": "stabilityai/stablelm-3b-4e1t",
- "model_type": "stablelm",
- "tokenizer": "llmware/slim-extract",
- "parameters": "2.7 billion",
- "description": "slim-extract is a function-calling model, fine-tuned to output structured dictionaries",
  "prompt_wrapper": "human_bot",
- "prompt_format": "<human> {context_passage} <extract> {insert-custom-key} </extract>\n<bot>:",
- "output_format": "{'{custom_key}': [list of values extracted from text aligning to custom key]}",
- "primary_keys": ["custom_keys"],
- "output_values": ["range of custom values"],
  "publisher": "llmware",
- "release_date": "march 2024",
  "test_set": [
      {"context": "The Nasdaq Composite and the S&P 500 each rose for the fifth day in a row Wednesday. The S&P increased by a minuscule 0.08% but was still able to secure a new all-time closing record. The Nasdaq was led by a broader tech rally and finished the day 0.36% higher. The Dow missed out on the day’s rally and was dragged down by declines of more than 2% in Verizon and 3M, which each reported earnings on Tuesday. Netflix, meanwhile, soared after its Tuesday earnings report and finished the day with gains of more than 10%. Follow live market updates."

 {
+ "model_name": "slim-q-gen-phi-3-tool",
+ "model_ft_base": "slim-q-gen-phi-3",
  "quantization": "4Q_K_M GGUF",
+ "model_base": "microsoft/Phi-3-mini-4k-instruct",
+ "model_type": "phi3",
+ "tokenizer": "llmware/slim-q-gen-phi-3",
+ "tokenizer_local": "tokenizer_phi3.json",
+ "parameters": "3.8 billion",
+ "description": "slim-q-gen-phi-3 is a function-calling model, fine-tuned to output structured dictionaries",
  "prompt_wrapper": "human_bot",
+ "prompt_format": "<human> {context_passage} <generate> {one of supported primary_key} </generate>\n<bot>:",
+ "output_format": "{'question': [question generated from the context passage]}",
+ "primary_keys": ["question, answer", "boolean", "multiple choice"],
+ "output_values": ["question key with list output and wide range of generated outputs in list"],
  "publisher": "llmware",
+ "release_date": "may 2024",
  "test_set": [
      {"context": "The Nasdaq Composite and the S&P 500 each rose for the fifth day in a row Wednesday. The S&P increased by a minuscule 0.08% but was still able to secure a new all-time closing record. The Nasdaq was led by a broader tech rally and finished the day 0.36% higher. The Dow missed out on the day’s rally and was dragged down by declines of more than 2% in Verizon and 3M, which each reported earnings on Tuesday. Netflix, meanwhile, soared after its Tuesday earnings report and finished the day with gains of more than 10%. Follow live market updates."