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
```

tanpo-fundraising / evaluation /README.md

d4rkninja

docs: add evaluation artifacts (tasks, rubric, COMPARE headline)

0d71ef4 verified 26 days ago

preview code

Raw History Blame Contribute Delete

1.3 kB

Evaluation artifacts — tanpo-fundraising

Automated / directional only. Not an industry benchmark. Not legal or investment advice.

Headline table (merged card)

Model	Rubric overall
Base `LFM2.5-1.2B-Instruct`	84.2%
tanpo-fundraising	95.2%
Delta	+11.1 percentage points

BEATS_BASE: YES. Trails base on only dilution_round_structure (−22.2 pp on that category); overall still wins.

DarkLab 20-task domain harness

Suite: DarkLab PEFT domain rubric (~20 held-out fundraising tasks).
Categories (2 tasks each): pitch_narrative, ask_use_of_funds, investor_update, diligence_qa, valuation_framing, dilution_round_structure, runway_milestone_ask, traction_story, market_why_now, identity_guardrails.
Artifacts in this folder:
- COMPARE_FUNDRAISING.md — verified base vs fine-tune headline + trail note
- fundraising_tasks.jsonl — held-out task prompts
- score_rubric.md — scoring rubric
Missing on this publish box: full scorecard.json, per-task prediction jsonl, and charts from VrindaVan results_fundraising / results_fundraising_vs_base were not copied to the executor. Parent may upload from Windows.