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

Libraries

How to use d4rkninja/tanpo-ops with Transformers:

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

pipe = pipeline("text-generation", model="d4rkninja/tanpo-ops")
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-ops")
model = AutoModelForCausalLM.from_pretrained("d4rkninja/tanpo-ops", 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-ops with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

d4rkninja commited on 24 days ago

Commit

f4ae83a

verified ·

1 Parent(s): a627ecc

docs: evaluation/COMPARE_OPS.md

Browse files

Files changed (1) hide show

evaluation/COMPARE_OPS.md +32 -0

evaluation/COMPARE_OPS.md ADDED Viewed

	@@ -0,0 +1,32 @@

+# DarkLab Base vs FT Compare
+**Generated:** 2026-09-18T15:32:32.450342+00:00
+**Base model:** `unsloth/LFM2.5-1.2B-Instruct`
+**Owner / creator:** DarkNinja Solutions / d4rkninja
+## Overall
+| Domain | Base % | FT % | Delta | BEATS_BASE |
+|---|---:|---:|---:|:---:|
+| `ops` | 89.5% | 90.7% | +1.2 | YES |
+## ops — per-category
+| Category | Base % | FT % | Delta | FT wins |
+|---|---:|---:|---:|:---:|
+| `capacity_planning` | 94.5% | 100.0% | +5.5 | yes |
+| `handoffs` | 100.0% | 92.6% | -7.4 | no |
+| `identity_guardrails` | 72.9% | 90.0% | +17.1 | yes |
+| `incident_postmortem` | 92.6% | 88.9% | -3.7 | no |
+| `okr_execution` | 83.3% | 94.5% | +11.1 | yes |
+| `operating_cadence` | 88.9% | 85.2% | -3.7 | no |
+| `sops` | 88.9% | 85.2% | -3.7 | no |
+| `vendor_ops` | 88.9% | 94.5% | +5.6 | yes |
+- **FT trails base in:** `handoffs`, `incident_postmortem`, `operating_cadence`, `sops`
+- Do **not** publish until a format patch lifts these categories.
+## Rule
+- Publish LoRA + merged + GGUF **only if** `BEATS_BASE` is true.
+- Automated rubric ≠ human preference.