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

Libraries

How to use jbae1213/fiqa-test with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "jbae1213/fiqa-test")

Transformers

How to use jbae1213/fiqa-test with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jbae1213/fiqa-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jbae1213/fiqa-test"
# 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/fiqa-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jbae1213/fiqa-test

SGLang

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

Unsloth Studio new

How to use jbae1213/fiqa-test 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/fiqa-test 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/fiqa-test to start chatting

Using HuggingFace Spaces for Unsloth

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

Load model with FastModel

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

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

jbae1213 commited on Mar 5

Commit

2e21175

verified ·

1 Parent(s): 8158c5f

Upload training_config.json with huggingface_hub

Browse files

Files changed (1) hide show

training_config.json +56 -0

training_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "stage": "sft",
+  "do_train": true,
+  "finetuning_type": "lora",
+  "model": "Qwen/Qwen3-4B-Instruct-2507",
+  "dataset": "llamafactory/fiqa",
+  "max_samples": null,
+  "eval_dataset": null,
+  "train_dataset_num_samples": 5500,
+  "eval_dataset_num_samples": null,
+  "quantization_bit": 4,
+  "load_in_4bit": true,
+  "load_in_16bit": false,
+  "lora_rank": 64,
+  "lora_r": 64,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "bias": "none",
+  "use_gradient_checkpointing": "unsloth",
+  "random_state": 3407,
+  "learning_rate": 0.00015,
+  "lr_scheduler_type": "cosine",
+  "warmup_ratio": 0.05,
+  "weight_decay": 0.0,
+  "adam_beta2": 0.999,
+  "num_train_epochs": 4.0,
+  "max_steps": -1,
+  "per_device_train_batch_size": 4,
+  "gradient_accumulation_steps": 4,
+  "seq_len": 2048,
+  "max_seq_length": 2048,
+  "logging_steps": 20,
+  "save_strategy": "steps",
+  "save_steps": 500,
+  "save_total_limit": 2,
+  "evaluation_strategy": "no",
+  "eval_steps": null,
+  "load_best_model_at_end": false,
+  "bf16": true,
+  "report_to": "none",
+  "dataset_num_proc": 4,
+  "seed": 3407,
+  "output_dir": "/root/jb/personas/finance/fiqa/finance_lora_unsloth_output/20260305_020931",
+  "adam_beta1": 0.9,
+  "packing": false,
+  "dataset_text_field": "text"
+}