Instructions to use d4rkninja/tanpo-product with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use d4rkninja/tanpo-product with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="d4rkninja/tanpo-product")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("d4rkninja/tanpo-product")
model = AutoModelForCausalLM.from_pretrained("d4rkninja/tanpo-product", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use d4rkninja/tanpo-product with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "d4rkninja/tanpo-product"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "d4rkninja/tanpo-product",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/d4rkninja/tanpo-product

SGLang

How to use d4rkninja/tanpo-product with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "d4rkninja/tanpo-product" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "d4rkninja/tanpo-product",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "d4rkninja/tanpo-product" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "d4rkninja/tanpo-product",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use d4rkninja/tanpo-product with Docker Model Runner:
```
docker model run hf.co/d4rkninja/tanpo-product
```

Tanpo Product

A compact product-strategy specialist (~1.2B) for roadmap tradeoffs, prioritization, metrics, and CEO-level product thinking — meant for local and inexpensive deployment.

Collection: Tanpo — Domain Specialists

Built on LiquidAI/LFM2.5-1.2B-Instruct (~1.17B parameters, 32,768-token context). Fine-tuned with Unsloth / PEFT LoRA via hub id unsloth/LFM2.5-1.2B-Instruct.

This repository hosts the merged Transformers weights (LoRA folded into the base).

Overview

Tanpo is a family of small domain-specialized business models for local, edge, and inexpensive deployment — one compact architecture, multiple focused specialists.

Tanpo Product is one specialist in that family — focused on its domain, not a general-purpose or frontier model.

Related formats:

LoRA adapter: d4rkninja/tanpo-product-LoRA
GGUF quants: d4rkninja/tanpo-product-GGUF — prefer Q4_K_M when available

Best For

Kill / keep / invest and prioritization write-ups
Roadmap sequencing and scope cuts
North-star metrics, OKRs, and operating cadence
Competitive positioning, pricing/monetization frames, and discovery synthesis

Not Designed For

Substituting primary customer research or user interviews
Authoritative market sizing or financial forecasts
Legal, security, or compliance decisions
General coding or non-product knowledge work

Why a Specialist?

Product decisions need structured tradeoffs more than generic chat. Fine-tuning a small model on product-workflow formats makes edge deployment practical without pulling in a large general model.

Evaluation

Internal automated evaluations. Treat scores as directional, not industry benchmarks.

Model	Rubric overall
Base `LFM2.5-1.2B-Instruct`	92.6%
tanpo-product	99.4%
Delta	+6.8 percentage points

Artifacts: evaluation/ — COMPARE_BASE.md, product_tasks.jsonl, score_rubric.md, evaluation/README.md.

Methodology: DarkLab automated domain evaluation on the product format-v1 fine-tune (~20 held-out tasks). Same prompts and generation config for base vs fine-tune.

About these numbers: Automated rubrics can reward structure over real-world quality; sample sizes are small; results may not transfer outside each task distribution.

Example Prompts

User: We have three bets for next quarter: (A) usage-based billing, (B) Salesforce sync, (C) mobile offline mode. Only engineering capacity for one. Recommend with kill criteria.
User: Draft a one-page PRD outline for an in-app 'saved views' feature for a B2B analytics product. Include problem, users, success metric, and non-goals.
User: Propose a north-star metric and 3 supporting input metrics for a vertical SaaS CRM for dental clinics.

Inference

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "d4rkninja/tanpo-product"
tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "system", "content": 'You are Tanpo Product, a practical product-strategy assistant.'},
    {"role": "user", "content": 'We have three bets for next quarter: (A) usage-based billing, (B) Salesforce sync, (C) mobile offline mode. Only engineering capacity for one. Recommend with kill criteria.'},
]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
out = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

Training

Verified from published adapter configs / training artifacts (no unverified hyperparams):

Field	Value
Method	LoRA (PEFT) via Unsloth FastLanguageModel on hub id `unsloth/LFM2.5-1.2B-Instruct` (Unsloth-compatible load of LiquidAI/LFM2.5-1.2B-Instruct)
LoRA rank (`r`)	16
LoRA alpha	16
LoRA dropout	0
Bias	none
Target modules	`q_proj`, `k_proj`, `v_proj`, `out_proj`, `in_proj`, `w1`, `w2`, `w3`
Task type	CAUSAL_LM

Merged via PEFT merge_and_unload into full weights in this repo.

Dataset

d4rkninja/tanpo-product-sft — ~10k format-fixed chat SFT examples (documented on the dataset card). Published specialist reflects the format-v1 continued-train path.

Limitations

Specialized: quality drops outside the product workflow distribution.
~1.2B scale: limited world knowledge and long-horizon reasoning vs larger models.
Can sound decisive when evidence is thin — require human judgment for consequential product bets.
Eval gains are rubric-based and directional only.

Responsible Use

Not a substitute for customer research, board fiduciary judgment, or professional analysis. Treat outputs as drafts for human product leaders.

License

license: other — inherits obligations from the upstream Liquid AI LFM2.5 / LFM base (LiquidAI/LFM2.5-1.2B-Instruct; training hub id unsloth/LFM2.5-1.2B-Instruct). Review Liquid AI’s license before commercial redistribution or redistribution of derivatives. Do not assume Apache-2.0 covers the merged weights.

Tanpo Model Family

Tanpo is a family of small domain-specialized business models for local, edge, and inexpensive deployment — one compact architecture, multiple focused specialists. Built for focused work, not every task.

Browse the set: Tanpo — Domain Specialists

Model	Specialization
Tanpo Marketing	Marketing, GTM, campaigns and messaging
Tanpo Product	Product strategy and product workflows
Tanpo Hiring	Recruiting and hiring workflows
Tanpo Deals	Sales, partnerships and negotiation
Tanpo Fundraising	Investor pitches, fundraising narratives, ask/use-of-funds

Domain	Merged	LoRA	GGUF
Marketing	tanpo-marketing	tanpo-marketing-LoRA	tanpo-marketing-GGUF
Product	tanpo-product	tanpo-product-LoRA	tanpo-product-GGUF
Hiring	tanpo-hiring	tanpo-hiring-LoRA	tanpo-hiring-GGUF
Deals	tanpo-deals	tanpo-deals-LoRA	tanpo-deals-GGUF
Fundraising	tanpo-fundraising	tanpo-fundraising-LoRA	tanpo-fundraising-GGUF

LiquidAI/LFM2.5-1.2B-Instruct (~1.17B, 32K)
  └── Unsloth load: unsloth/LFM2.5-1.2B-Instruct
        └── Tanpo Product (domain SFT via LoRA)
              ├── Merged  → d4rkninja/tanpo-product
              ├── LoRA    → d4rkninja/tanpo-product-LoRA
              └── GGUF    → d4rkninja/tanpo-product-GGUF