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

Libraries

How to use d4rkninja/tanpo-finance with Transformers:

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

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

d4rkninja commited on 27 days ago

Commit

6b33725

verified ·

1 Parent(s): f38c330

docs: evaluation/COMPARE.json

Browse files

Files changed (1) hide show

evaluation/COMPARE.json +260 -0

evaluation/COMPARE.json ADDED Viewed

	@@ -0,0 +1,260 @@

+{
+  "benchmark": "darklab-base-vs-ft-v2",
+  "generated_at": "2026-09-18T16:55:59.037166+00:00",
+  "base": "unsloth/LFM2.5-1.2B-Instruct",
+  "owner": "DarkNinja Solutions",
+  "creator": "d4rkninja",
+  "scoring": "deterministic_rubric_v2_strict",
+  "model_order": [
+    "finance"
+  ],
+  "base_models": {
+    "finance": {
+      "display_name": "base/tanpo-finance",
+      "key": "finance",
+      "model_id": "base:unsloth/LFM2.5-1.2B-Instruct",
+      "base": "unsloth/LFM2.5-1.2B-Instruct",
+      "status": "ok",
+      "error": null,
+      "lora_path": null,
+      "load_seconds": 20.2,
+      "gen_seconds": 156.0,
+      "overall_pct": 93.08,
+      "quality_avg": 6.54,
+      "n_tasks": 20,
+      "by_category": {
+        "unit_economics": {
+          "score_pct": 94.45,
+          "quality_avg": 6.36,
+          "n": 2
+        },
+        "runway_cash": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "pricing_finance": {
+          "score_pct": 100.0,
+          "quality_avg": 7.4,
+          "n": 2
+        },
+        "saas_metrics": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "budget_tradeoffs": {
+          "score_pct": 94.45,
+          "quality_avg": 7.51,
+          "n": 2
+        },
+        "burn_efficiency": {
+          "score_pct": 94.45,
+          "quality_avg": 7.36,
+          "n": 2
+        },
+        "cohort_revenue": {
+          "score_pct": 94.45,
+          "quality_avg": 5.91,
+          "n": 2
+        },
+        "cost_structure": {
+          "score_pct": 100.0,
+          "quality_avg": 7.5,
+          "n": 2
+        },
+        "forecast_scenario": {
+          "score_pct": 94.45,
+          "quality_avg": 6.36,
+          "n": 2
+        },
+        "identity_guardrails": {
+          "score_pct": 58.57,
+          "quality_avg": 0.96,
+          "n": 2
+        }
+      },
+      "categories": [
+        "budget_tradeoffs",
+        "burn_efficiency",
+        "cohort_revenue",
+        "cost_structure",
+        "forecast_scenario",
+        "identity_guardrails",
+        "pricing_finance",
+        "runway_cash",
+        "saas_metrics",
+        "unit_economics"
+      ]
+    }
+  },
+  "ft_models": {
+    "finance": {
+      "display_name": "tanpo-finance",
+      "key": "finance",
+      "model_id": "peft:tanpo-finance",
+      "base": "unsloth/LFM2.5-1.2B-Instruct",
+      "status": "ok",
+      "error": null,
+      "lora_path": "C:\\Users\\alien\\tanpo-finance-lora-format-v2",
+      "load_seconds": 8.9,
+      "gen_seconds": 185.9,
+      "overall_pct": 98.44,
+      "quality_avg": 7.86,
+      "n_tasks": 20,
+      "by_category": {
+        "unit_economics": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "runway_cash": {
+          "score_pct": 100.0,
+          "quality_avg": 8.5,
+          "n": 2
+        },
+        "pricing_finance": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "saas_metrics": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "budget_tradeoffs": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "burn_efficiency": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "cohort_revenue": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "cost_structure": {
+          "score_pct": 94.45,
+          "quality_avg": 7.36,
+          "n": 2
+        },
+        "forecast_scenario": {
+          "score_pct": 100.0,
+          "quality_avg": 8.0,
+          "n": 2
+        },
+        "identity_guardrails": {
+          "score_pct": 90.0,
+          "quality_avg": 6.75,
+          "n": 2
+        }
+      },
+      "categories": [
+        "budget_tradeoffs",
+        "burn_efficiency",
+        "cohort_revenue",
+        "cost_structure",
+        "forecast_scenario",
+        "identity_guardrails",
+        "pricing_finance",
+        "runway_cash",
+        "saas_metrics",
+        "unit_economics"
+      ]
+    }
+  },
+  "compares": {
+    "finance": {
+      "base_pct": 93.08,
+      "ft_pct": 98.44,
+      "delta": 5.36,
+      "BEATS_BASE": true,
+      "categories": [
+        {
+          "category": "budget_tradeoffs",
+          "base_pct": 94.45,
+          "ft_pct": 100.0,
+          "delta": 5.55,
+          "ft_wins": true
+        },
+        {
+          "category": "burn_efficiency",
+          "base_pct": 94.45,
+          "ft_pct": 100.0,
+          "delta": 5.55,
+          "ft_wins": true
+        },
+        {
+          "category": "cohort_revenue",
+          "base_pct": 94.45,
+          "ft_pct": 100.0,
+          "delta": 5.55,
+          "ft_wins": true
+        },
+        {
+          "category": "cost_structure",
+          "base_pct": 100.0,
+          "ft_pct": 94.45,
+          "delta": -5.55,
+          "ft_wins": false
+        },
+        {
+          "category": "forecast_scenario",
+          "base_pct": 94.45,
+          "ft_pct": 100.0,
+          "delta": 5.55,
+          "ft_wins": true
+        },
+        {
+          "category": "identity_guardrails",
+          "base_pct": 58.57,
+          "ft_pct": 90.0,
+          "delta": 31.43,
+          "ft_wins": true
+        },
+        {
+          "category": "pricing_finance",
+          "base_pct": 100.0,
+          "ft_pct": 100.0,
+          "delta": 0.0,
+          "ft_wins": false
+        },
+        {
+          "category": "runway_cash",
+          "base_pct": 100.0,
+          "ft_pct": 100.0,
+          "delta": 0.0,
+          "ft_wins": false
+        },
+        {
+          "category": "saas_metrics",
+          "base_pct": 100.0,
+          "ft_pct": 100.0,
+          "delta": 0.0,
+          "ft_wins": false
+        },
+        {
+          "category": "unit_economics",
+          "base_pct": 94.45,
+          "ft_pct": 100.0,
+          "delta": 5.55,
+          "ft_wins": true
+        }
+      ],
+      "categories_ft_trails": [
+        "cost_structure",
+        "pricing_finance",
+        "runway_cash",
+        "saas_metrics"
+      ],
+      "base_quality_avg": 6.54,
+      "ft_quality_avg": 7.86
+    }
+  },
+  "total_seconds": 176.3
+}