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

d2bce9f

verified ·

1 Parent(s): f9c319d

Upload evaluation/base_compare/scorecard_base.json with huggingface_hub

Browse files

Files changed (1) hide show

evaluation/base_compare/scorecard_base.json +86 -0

evaluation/base_compare/scorecard_base.json ADDED Viewed

	@@ -0,0 +1,86 @@

+{
+  "models": {
+    "fundraising": {
+      "display_name": "base/tanpo-fundraising",
+      "key": "fundraising",
+      "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": 8.4,
+      "gen_seconds": 219.1,
+      "overall_pct": 84.19,
+      "quality_avg": 5.62,
+      "n_tasks": 20,
+      "by_category": {
+        "pitch_narrative": {
+          "score_pct": 83.34,
+          "quality_avg": 6.08,
+          "n": 2
+        },
+        "ask_use_of_funds": {
+          "score_pct": 83.34,
+          "quality_avg": 6.08,
+          "n": 2
+        },
+        "investor_update": {
+          "score_pct": 88.89,
+          "quality_avg": 5.62,
+          "n": 2
+        },
+        "diligence_qa": {
+          "score_pct": 94.45,
+          "quality_avg": 6.41,
+          "n": 2
+        },
+        "valuation_framing": {
+          "score_pct": 88.89,
+          "quality_avg": 6.12,
+          "n": 2
+        },
+        "dilution_round_structure": {
+          "score_pct": 88.89,
+          "quality_avg": 6.22,
+          "n": 2
+        },
+        "runway_milestone_ask": {
+          "score_pct": 83.34,
+          "quality_avg": 6.48,
+          "n": 2
+        },
+        "traction_story": {
+          "score_pct": 88.89,
+          "quality_avg": 6.72,
+          "n": 2
+        },
+        "market_why_now": {
+          "score_pct": 83.34,
+          "quality_avg": 5.48,
+          "n": 2
+        },
+        "identity_guardrails": {
+          "score_pct": 58.57,
+          "quality_avg": 0.96,
+          "n": 2
+        }
+      },
+      "categories": [
+        "ask_use_of_funds",
+        "diligence_qa",
+        "dilution_round_structure",
+        "identity_guardrails",
+        "investor_update",
+        "market_why_now",
+        "pitch_narrative",
+        "runway_milestone_ask",
+        "traction_story",
+        "valuation_framing"
+      ]
+    }
+  },
+  "base": "unsloth/LFM2.5-1.2B-Instruct",
+  "model_order": [
+    "fundraising"
+  ]
+}