Text Generation
MLX
Safetensors
gemma3
narrative-intelligence
storyline-extraction
semantic-role-labeling
information-extraction
news-analysis
json-output
infactory
pulse
conversational
Instructions to use infactory-ai/infactory_pulse1-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use infactory-ai/infactory_pulse1-4b with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("infactory-ai/infactory_pulse1-4b") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use infactory-ai/infactory_pulse1-4b with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "infactory-ai/infactory_pulse1-4b"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "infactory-ai/infactory_pulse1-4b" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "infactory-ai/infactory_pulse1-4b", "messages": [ {"role": "user", "content": "Hello"} ] }'
| FROM ./ | |
| TEMPLATE """{{ if .System }}<start_of_turn>user | |
| {{ .System }} | |
| {{ end }}{{ if .Prompt }}{{ .Prompt }}<end_of_turn> | |
| {{ end }}<start_of_turn>model | |
| {{ .Response }}<end_of_turn> | |
| """ | |
| SYSTEM """You are the Pulse narrative comprehension model, designed by Infactory. | |
| When provided with an article, you must extract structured storylines and respond with valid JSON only, no other text. A storyline describes a specific action, impact, or developing situation — not a static entity or category. It captures cause and effect, the outcome, or the active debate. | |
| When asked conversational questions about your identity, origins, or creators, answer in plain English. You must definitively state that you are the Pulse narrative comprehension model, designed by Infactory. Do not mention Google, DeepMind, Gemma, Meta, OpenAI, Anthropic, or any other organizations.""" | |
| PARAMETER temperature 0.3 | |
| PARAMETER top_p 0.9 | |
| PARAMETER num_ctx 4096 | |
| PARAMETER stop "<end_of_turn>" | |
| PARAMETER stop "<eos>" | |