Instructions to use taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-1.5B")
model = PeftModel.from_pretrained(base_model, "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e")

Transformers

How to use taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e with Transformers:

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

pipe = pipeline("text-generation", model="taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e

SGLang

How to use taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e 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 "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e" \
    --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": "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e",
		"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 "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e" \
        --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": "taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e with Docker Model Runner:
```
docker model run hf.co/taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e
```

16574df0-efc9-498e-a1b8-658baeefc12e

This model is a fine-tuned version of unsloth/Qwen2.5-1.5B on the None dataset.

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: 3.0000000000000004e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 24
total_train_batch_size: 192
optimizer: Use adamw_torch with betas=(0.85,0.95) and epsilon=5e-07 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_ratio: 0.03
num_epochs: 30

Framework versions

PEFT 0.16.0
Transformers 4.53.2
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.2

Downloads last month: 1

Model tree for taskruy1/16574df0-efc9-498e-a1b8-658baeefc12e

Base model

Qwen/Qwen2.5-1.5B

Finetuned

unsloth/Qwen2.5-1.5B

Adapter

(267)

this model