Instructions to use d4rkninja/tanpo-ops with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
|
Download evaluation/COMPARE_OPS.md from d4rkninja/tanpo-ops: direct link, hf CLI and curl.
- Browser
- Download file 1.11 kB
-
https://huggingface.co/d4rkninja/tanpo-ops/resolve/main/evaluation/COMPARE_OPS.md
- Command line
-
hf download hf://d4rkninja/tanpo-ops/evaluation/COMPARE_OPS.md
-
curl -L -o COMPARE_OPS.md https://huggingface.co/d4rkninja/tanpo-ops/resolve/main/evaluation/COMPARE_OPS.md
1.11 kB
| # 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. | |