saas-business-strategist-agent

Quick start (Ollama, runs on a CPU):

ollama run hf.co/profullstack/saas-business-strategist-agent-GGUF "How should a 3-person SaaS price its first plan?"

Needs Ollama 0.3.13 or newer (curl -fsSL https://ollama.com/install.sh | sh, or w3bs install ollama). The GGUF is at profullstack/saas-business-strategist-agent-GGUF; this repo is the LoRA adapter.

base	Qwen/Qwen2.5-0.5B-Instruct
corpus	3672 documents from topic:business, topic:saas, topic:crypto, pit:saas, pit:business, pit:crypto
training	400 LoRA steps (r=8, seq_len=256, lr=0.0002) on the c0mpute network (infernet.text.train, job a8b79035-14b0-44a1-8bdc-72143c41478c, receipt hash sha256:21a96aafae47791cd3dd500b888b6f7792952d04fe416a4862139f047d4be593 matches this adapter)
held-out perplexity	40.9 to 26.0
adapter sha256	21a96aafae47791cd3dd500b888b6f7792952d04fe416a4862139f047d4be593

Built with the c0mpute example. Sources are rssamplifier.com topic feeds and pit.world search; the corpus is not redistributed here.

Use from Python (adapter)

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("profullstack/saas-business-strategist-agent")
model = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct"), "profullstack/saas-business-strategist-agent")
msgs = [{"role": "system", "content": "You are saas-business-strategist-agent. You give concise, practical SaaS and business strategy grounded in what independent writers on business, SaaS and crypto are publishing."},
        {"role": "user", "content": "How should a 3-person SaaS price its first plan?"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")
print(tok.decode(model.generate(ids, max_new_tokens=300)[0][ids.shape[1]:], skip_special_tokens=True))

Best results come from putting fresh search results in the prompt (the example's chat.py uses pit.world search): a sub-1B model supplies the voice, not the facts.