Instructions to use ccortezb/FinOptix-14B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ccortezb/FinOptix-14B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ccortezb/FinOptix-14B-v2")
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("ccortezb/FinOptix-14B-v2")
model = AutoModelForCausalLM.from_pretrained("ccortezb/FinOptix-14B-v2", 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 ccortezb/FinOptix-14B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ccortezb/FinOptix-14B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ccortezb/FinOptix-14B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ccortezb/FinOptix-14B-v2

SGLang

How to use ccortezb/FinOptix-14B-v2 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 "ccortezb/FinOptix-14B-v2" \
    --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": "ccortezb/FinOptix-14B-v2",
		"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 "ccortezb/FinOptix-14B-v2" \
        --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": "ccortezb/FinOptix-14B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use ccortezb/FinOptix-14B-v2 with Docker Model Runner:
```
docker model run hf.co/ccortezb/FinOptix-14B-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

FinOptix-14B v2 — Your FinOps Architect in 14 Billion Parameters

FinOptix-14B v2 is an open-weights FinOps specialist fine-tuned on Qwen 2.5 14B Instruct. It audits infrastructure-as-code, reasons about AWS cost and commitments, triages incidents into remediation-as-code, and analyzes data-pipeline cost — fully offline on a single GPU.

v2 is a re-train of the original FinOptix-14B (HF "Build Small" hackathon, Jun 2026). The v1 repo stays as the historical baseline.

16-bit model: ccortezb/FinOptix-14B-v2 (this repo)
GGUF (Ollama / llama.cpp): ccortezb/FinOptix-14B-v2-GGUF — Q4_K_M (~~9GB, portable) and Q6_K (~~12GB, higher fidelity)

What's new in v2

v1 was trained for a stack that has since evolved. v2 re-aligns the model to the current ecosystem and adds three new domains:

Capability	v1	v2
Terraform HCL audit (rightsizing, tagging, Graviton, gp2→gp3, lifecycle)	✅	✅ updated
AWS Cost Explorer JSON + anomalies	✅	✅
Savings Plans / Reserved Instances coverage & utilization	—	✅ new
BYaML v2 Architecture Graph reasoning (blast radius, cost chains, owner attribution)	YAML lint only	✅ graph-first
Remo — incident triage + remediation-as-code	—	✅ new
sofe-dbt — data-engineering FinOps (Athena bytes scanned, incremental vs full-refresh, partitioning)	—	✅ new
FinOps Q&A	✅	✅

Key shift: BYaML moved from "validate this YAML" to "reason over the derived Architecture Graph" — the model computes blast radius and cost propagation over nodes (aws.<resource>) and typed edges, matching the real byaml-spec v0.4 schema.

Training

Parameter	Value
Base model	`Qwen/Qwen2.5-14B-Instruct` (4-bit via Unsloth)
Method	QLoRA (r=16, α=32, dropout=0.05)
Framework	Unsloth + TRL (SFTTrainer)
Dataset	966 examples (265 v1 + 701 new, deterministic generators)
Hardware	Modal A100-80GB
Duration	~20 minutes, 3 epochs, 183 steps
Final train loss	0.28
Cost	~$2

The dataset was built with deterministic per-domain generators faithful to the real policy definitions (sofe-dbt policies, SOFE savings collectors, the byaml-spec v0.4 schema) — every cost figure is derived from the input, never fabricated.

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ccortezb/FinOptix-14B-v2", device_map="auto")
tok = AutoTokenizer.from_pretrained("ccortezb/FinOptix-14B-v2")

messages = [
    {"role": "system", "content": "You are FinOptix-14B, a FinOps specialist. Costs are derived from real data, never invented."},
    {"role": "user", "content": "Audit this dbt model: fct_events runs daily with --full-refresh, bytes_scanned_last_run=1.2TB, is_incremental=1."},
]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=350, do_sample=False, repetition_penalty=1.1)
print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))

Ollama (GGUF)

ollama run hf.co/ccortezb/FinOptix-14B-v2-GGUF:Q4_K_M
# or higher fidelity:
ollama run hf.co/ccortezb/FinOptix-14B-v2-GGUF:Q6_K

Requires ~10GB RAM/VRAM (Q4_K_M) or ~13GB (Q6_K).

Example tasks

dbt cost audit → detects --full-refresh on a 1.2TB incremental model, recommends partition_by + removing the daily full-refresh (~$180/mo Athena savings), classifies as Optimize.

Incident triage (Remo) → classifies severity, finds root cause, and emits remediation-as-code (e.g. Terraform aws_s3_bucket_public_access_block for a recurring public bucket).

Architecture Graph blast radius → given a BYaML v0.4 graph, computes which nodes break if a node fails and which cost chains drive spend.

Limitations

Trained on synthetic data modeled after real patterns — no customer data.
Does not execute commands or call live AWS APIs; it reasons and recommends.
Not a substitute for professional financial/compliance advice.
Cost figures are illustrative unless real scan stats are provided in the prompt.

License

Apache-2.0. Built by Carlos Cortez — AWS Community Hero. LinkedIn · X · GitHub · AWS Heroes

Downloads last month: 30

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for ccortezb/FinOptix-14B-v2

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Finetuned

(449)

this model

Quantizations

2 models

ccortezb
/

FinOptix-14B-v2