Instructions to use coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full with Transformers:

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

pipe = pipeline("text-generation", model="coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full")
model = AutoModelForCausalLM.from_pretrained("coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full

SGLang

How to use coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full 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 "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full" \
    --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": "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full",
		"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 "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full" \
        --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": "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full",
    max_seq_length=2048,
)

Docker Model Runner
How to use coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full with Docker Model Runner:
```
docker model run hf.co/coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full
```

📈 FinCode-Reasoning-3B (Full Weights)

FinCode-Reasoning-3B is an experimental, fine-tuned language model based on Qwen/Qwen2.5-3B-Instruct. Fine-tuned using Unsloth, it is engineered to generate executable Python code for quantitative financial modeling, accounting boundary checks, and algorithmic calculations.

ℹ️ Project Context: This is an open-source research initiative by coslinedev exploring domain-specific SFT for local LLMs. The model architecture delegates exact arithmetic logic to an isolated Python execution sandbox through structured code generation, bypassing direct LLM mental arithmetic hallucinations.

📁 Repository Structure

This repository contains the full merged model weights (~6.18 GB), ready for direct inference without requiring extra LoRA adapter layers:

model-00001-of-00002.safetensors & model-00002-of-00002.safetensors: Full model weight shards.
model.safetensors.index.json: Index mapping for sharded weight loading.
chat_template.jinja: Jinja chat formatting template for system/user prompt alignment.
tokenizer.json & tokenizer_config.json: Tokenizer assets inherited from Qwen2.5.
config.json & generation_config.json: Model architecture and generation configuration parameters.

🛠️ Usage Example

You can load and run this model locally or on Google Colab using Hugging Face transformers:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "Write a Python function to calculate Double Declining Balance (DDB) depreciation with a salvage floor constraint."

messages = [
    {"role": "system", "content": "You are a financial engineering assistant. Output clean, executable Python code with explicit boundary constraint handling."},
    {"role": "user", "content": prompt}
]

formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([formatted_prompt], return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.2)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
⚙️ Key Design PrinciplesExecution Sandbox First: Direct numerical output is delegated to the Python interpreter executing the generated script, eliminating calculation hallucinations.Boundary Constraint Enforcer: Fine-tuned to enforce strict business limits within code logic (e.g., depreciation = min(book_value * ddb_rate, max(book_value - salvage, 0.0))).Hardware-Friendly Deployment: Compact 3B parameter footprint requires ~6–8 GB VRAM in float16, running smoothly on free-tier GPUs like Google Colab T4.📊 Preliminary Benchmark ($n=100$)Evaluated on 100 synthetic quantitative financial tasks (DDB depreciation schedules, Black-Scholes pricing, WACC calculations, Tax Shield bounds, DCF models).Both models were benchmarked under the exact same setup: output code was passed through an isolated Python execution sandbox to verify execution and mathematical correctness.ModelSetupCode Pass Rate (Pass@1)Valid Syntax RateAvg Generation Latency*FinCode-Reasoning-3B (Ours)Local + Python Sandbox98.0%99.5%0.85sQwen2.5-3B-Instruct (Base)Local + Python Sandbox82.0%85.0%0.82s*Inference latency measured on a free-tier Google Colab T4 GPU (float16 precision). Does not include sandbox execution overhead.⚠️ Known Limitations & DisclaimersSample Size Noise: Evaluated on $n=100$ tasks, carrying an estimated statistical error margin of $\pm 4\%$.Interpreter Dependency: The model generates code logic; guaranteed mathematical execution requires an active Python sandbox environment.Out-of-Distribution (OOD) Testing: Test tasks share parametric generator logic with the training set. A fully independent, held-out evaluation dataset is planned for future iterations.📬 Feedback & ContactIf you spot technical inaccuracies, unexpected code generation logic, or have ideas for improvement, feel free to contribute!Hugging Face Discussions: Open a thread in the Community tab of this repository.Pull Requests: PRs improving configuration files, documentation, or evaluation scripts are always welcome.📜 LicenseLicensed under the Apache 2.0 License, aligning with base Qwen2.5 model licensing.

Downloads last month: 885

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for coslinedev/Qwen2.5-3B-FinCode-Reasoning-Full

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1509)

this model