Instructions to use jbae1213/budgeting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jbae1213/budgeting with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "jbae1213/budgeting")

Transformers

How to use jbae1213/budgeting with Transformers:

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

pipe = pipeline("text-generation", model="jbae1213/budgeting")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jbae1213/budgeting", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jbae1213/budgeting with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jbae1213/budgeting"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jbae1213/budgeting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jbae1213/budgeting

SGLang

How to use jbae1213/budgeting 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 "jbae1213/budgeting" \
    --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": "jbae1213/budgeting",
		"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 "jbae1213/budgeting" \
        --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": "jbae1213/budgeting",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use jbae1213/budgeting 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 jbae1213/budgeting 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 jbae1213/budgeting to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jbae1213/budgeting to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="jbae1213/budgeting",
    max_seq_length=2048,
)

Docker Model Runner
How to use jbae1213/budgeting with Docker Model Runner:
```
docker model run hf.co/jbae1213/budgeting
```

jbae1213 commited on Mar 5

Commit

4cefee2

verified ·

1 Parent(s): 7c2803d

Upload train_config.json with huggingface_hub

Browse files

Files changed (1) hide show

train_config.json +54 -0

train_config.json ADDED Viewed

	@@ -0,0 +1,54 @@

+{
+  "dataset": {
+    "path": "/root/jb/personas/finance/budgeting/data/qa_pairs_train.json",
+    "num_train_samples": 1148,
+    "dataset_text_field": "text"
+  },
+  "validation_dataset": {
+    "path": "/root/jb/personas/finance/budgeting/data/qa_pairs_val.json",
+    "num_eval_samples": 144
+  },
+  "model": {
+    "name": "Qwen/Qwen3-4B-Instruct-2507",
+    "load_in_4bit": false
+  },
+  "lora": {
+    "r": 16,
+    "lora_alpha": 16,
+    "lora_dropout": 0.05,
+    "bias": "none",
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ],
+    "random_state": 3407
+  },
+  "training": {
+    "output_dir": "/root/jb/personas/finance/budgeting/finetune_lora_output/2026-03-04_04-18-09",
+    "max_seq_length": 2048,
+    "num_train_epochs": 3.0,
+    "max_steps": -1,
+    "per_device_train_batch_size": 2,
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.01,
+    "warmup_ratio": 0.03,
+    "lr_scheduler_type": "cosine",
+    "optim": "adamw_torch",
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.95,
+    "bf16": true,
+    "seed": 3407,
+    "logging_steps": 10,
+    "save_strategy": "steps",
+    "save_steps": 200,
+    "save_total_limit": 2,
+    "dataset_num_proc": 4,
+    "packing": false
+  }
+}