Instructions to use ohthisischichi/viet-cultural-qa-qwen2.5-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ohthisischichi/viet-cultural-qa-qwen2.5-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "ohthisischichi/viet-cultural-qa-qwen2.5-lora")

Transformers

How to use ohthisischichi/viet-cultural-qa-qwen2.5-lora with Transformers:

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

pipe = pipeline("text-generation", model="ohthisischichi/viet-cultural-qa-qwen2.5-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ohthisischichi/viet-cultural-qa-qwen2.5-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ohthisischichi/viet-cultural-qa-qwen2.5-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ohthisischichi/viet-cultural-qa-qwen2.5-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohthisischichi/viet-cultural-qa-qwen2.5-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ohthisischichi/viet-cultural-qa-qwen2.5-lora

SGLang

How to use ohthisischichi/viet-cultural-qa-qwen2.5-lora 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 "ohthisischichi/viet-cultural-qa-qwen2.5-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohthisischichi/viet-cultural-qa-qwen2.5-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ohthisischichi/viet-cultural-qa-qwen2.5-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohthisischichi/viet-cultural-qa-qwen2.5-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ohthisischichi/viet-cultural-qa-qwen2.5-lora with Docker Model Runner:
```
docker model run hf.co/ohthisischichi/viet-cultural-qa-qwen2.5-lora
```

viet-cultural-qa-qwen2.5-lora

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6759

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8629	0.0616	200	0.8580
0.7844	0.1233	400	0.8019
0.7311	0.1849	600	0.7703
0.7329	0.2465	800	0.7493
0.7079	0.3082	1000	0.7341
0.6902	0.3698	1200	0.7232
0.6888	0.4314	1400	0.7133
0.6997	0.4931	1600	0.7049
0.6709	0.5547	1800	0.6994
0.6591	0.6163	2000	0.6946
0.6728	0.6780	2200	0.6895
0.6629	0.7396	2400	0.6857
0.6489	0.8012	2600	0.6828
0.6513	0.8629	2800	0.6793
0.6334	0.9245	3000	0.6772
0.6405	0.9861	3200	0.6761
0.6148	1.0	3245	0.6759

Framework versions

PEFT 0.19.1
Transformers 5.8.1
Pytorch 2.10.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: 783

Model tree for ohthisischichi/viet-cultural-qa-qwen2.5-lora

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1276)

this model