aymandakir-gh/gh-pulse

GH Pulse (1.7B)

GH Pulse is part of GH AI, the open model family from Growthackers, an Italian growth-marketing agency: GH Spark (0.6B), GH Pulse (1.7B) and GH Apex (4B). Best for: everyday growth-marketing assistant.

It is a LoRA fine-tune of Qwen/Qwen3-1.7B (Apache-2.0) on Growthackers' public growth-marketing knowledge (playbooks, metrics library, glossary, acquisition / content / SEO / CRO / AI-tool notes) plus an open general-chat slice (HuggingFaceTB/smoltalk, Apache-2.0). Trained on a single laptop CPU.

Evaluation (base → GH Pulse)

Metric	Qwen3-1.7B	GH Pulse
Loss on held-out GH notes (lower is better)	3.300	2.214
ARC-Easy (zero-shot)	63.0%	65.5%
ARC-Challenge (zero-shot)	43.5%	46.5%

Usage

ollama create gh-pulse -f Modelfile && ollama run gh-pulse
llama-server -m gh-pulse-Q4_K_M.gguf --jinja -c 8192   # OpenAI-compatible API

Use non-thinking mode (enable_thinking=False); the GH system prompt is baked into the Modelfile.

Training data and privacy

Only generic-knowledge notes were used. Notes mentioning any client were dropped; people's names, emails, phone numbers, IBANs, ad-account IDs and API keys were scrubbed; HR, finance, partner, legal and client-success material was excluded entirely.

Limitations

Small model: it can invent facts, statistics and URLs, and its arithmetic is unreliable. No internet access. Verify figures before using its output with clients. Known issue: asked for contact details it can still guess Growthackers addresses (e.g. a growthackers.it site/email); the official site is https://gh.company.