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

Libraries

How to use d4rkninja/tanpo-fundraising with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("d4rkninja/tanpo-fundraising")
model = AutoModelForCausalLM.from_pretrained("d4rkninja/tanpo-fundraising", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use d4rkninja/tanpo-fundraising with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "d4rkninja/tanpo-fundraising"
# 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-fundraising",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use d4rkninja/tanpo-fundraising 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-fundraising" \
    --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-fundraising",
		"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-fundraising" \
        --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-fundraising",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

d4rkninja commited on 27 days ago

Commit

1e62180

verified ·

1 Parent(s): 666c98d

Upload evaluation/ft/SCORECARD.md with huggingface_hub

Browse files

Files changed (1) hide show

evaluation/ft/SCORECARD.md +45 -0

evaluation/ft/SCORECARD.md ADDED Viewed

	@@ -0,0 +1,45 @@

+# DarkLab 3-Model PEFT Scorecard
+**Generated:** 2026-09-18T06:00:18.662821+00:00
+**Base:** `unsloth/LFM2.5-1.2B-Instruct`
+**Scoring:** deterministic rubric v2 strict (domain tasks, not identity-only)
+**Owner / creator:** DarkNinja Solutions / d4rkninja
+## Overall
+| Metric | tanpo-fundraising |
+|---| ---: |
+| **Rubric overall %** | 95.2% |
+| Heuristic quality (0–10) | 7.45 |
+| Tasks | 20 |
+## Narrative
+- **Top domain score:** `tanpo-fundraising` at **95.2%** (on its own domain task set).
+- **Spread across domains (max−min):** 0.0 pts.
+- Each model is scored on **domain-specific** tasks (marketing / product / hiring / deals / fundraising). Overall % is **not** cross-domain comparable like-for-like — use per-category charts.
+- Unsolicited identity dumps are penalized; capability tasks expect structure, specificity, and next actions.
+## tanpo-fundraising — per-category
+| Category | Rubric % | Quality | n |
+|---|---:|---:|---:|
+| `ask_use_of_funds` | 100.0% | 8.50 | 2 |
+| `diligence_qa` | 100.0% | 7.90 | 2 |
+| `dilution_round_structure` | 66.7% | 4.56 | 2 |
+| `identity_guardrails` | 85.7% | 6.14 | 2 |
+| `investor_update` | 100.0% | 9.00 | 2 |
+| `market_why_now` | 100.0% | 7.30 | 2 |
+| `pitch_narrative` | 100.0% | 7.90 | 2 |
+| `runway_milestone_ask` | 100.0% | 8.50 | 2 |
+| `traction_story` | 100.0% | 7.30 | 2 |
+| `valuation_framing` | 100.0% | 7.40 | 2 |
+- LoRA: `C:\Users\alien\tanpo-fundraising-lora`
+- Load 8.6s · Gen 528.7s
+## Limitations
+- Automated rubric ≠ human preference.
+- Domain models are evaluated on different task sets — compare within domain.
+- Strict v2 reduces easy keyword passes; valid paraphrases can still false-negative.