Instructions to use AhmedZaky1/authorship_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AhmedZaky1/authorship_model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "AhmedZaky1/authorship_model")

Transformers

How to use AhmedZaky1/authorship_model with Transformers:

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

pipe = pipeline("text-generation", model="AhmedZaky1/authorship_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AhmedZaky1/authorship_model", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AhmedZaky1/authorship_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AhmedZaky1/authorship_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AhmedZaky1/authorship_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AhmedZaky1/authorship_model

SGLang

How to use AhmedZaky1/authorship_model 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 "AhmedZaky1/authorship_model" \
    --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": "AhmedZaky1/authorship_model",
		"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 "AhmedZaky1/authorship_model" \
        --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": "AhmedZaky1/authorship_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AhmedZaky1/authorship_model with Docker Model Runner:
```
docker model run hf.co/AhmedZaky1/authorship_model
```

authorship_model

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the authorship_train dataset. It achieves the following results on the evaluation set:

Loss: 0.4835

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.3347	0.0528	500	0.6354
1.3194	0.1057	1000	0.6109
1.2027	0.1585	1500	0.5906
1.2360	0.2114	2000	0.5835
1.2672	0.2642	2500	0.5752
1.1666	0.3171	3000	0.5580
1.1543	0.3699	3500	0.5537
1.1933	0.4227	4000	0.5499
1.2075	0.4756	4500	0.5418
1.0687	0.5284	5000	0.5443
1.0309	0.5813	5500	0.5371
0.9416	0.6341	6000	0.5339
1.1705	0.6869	6500	0.5248
0.9056	0.7398	7000	0.5215
1.0791	0.7926	7500	0.5182
1.0082	0.8455	8000	0.5137
1.1300	0.8983	8500	0.5123
1.0804	0.9512	9000	0.5095
0.9295	1.0039	9500	0.5073
0.9995	1.0568	10000	0.5065
1.0430	1.1096	10500	0.5050
1.0754	1.1624	11000	0.5025
1.0258	1.2153	11500	0.5010
1.0720	1.2681	12000	0.4990
1.0141	1.3210	12500	0.4977
0.9102	1.3738	13000	0.4960
1.0301	1.4266	13500	0.4951
0.8990	1.4795	14000	0.4934
1.0046	1.5323	14500	0.4922
0.8761	1.5852	15000	0.4909
1.0435	1.6380	15500	0.4897
0.9703	1.6909	16000	0.4875
0.8901	1.7437	16500	0.4857
0.9523	1.7965	17000	0.4855
0.9663	1.8494	17500	0.4838
0.9741	1.9022	18000	0.4831
0.9686	1.9551	18500	0.4817
0.8208	2.0078	19000	0.4860
0.9067	2.0607	19500	0.4867
0.8943	2.1135	20000	0.4873
0.9204	2.1663	20500	0.4863
0.8343	2.2192	21000	0.4863
0.8542	2.2720	21500	0.4871
0.9198	2.3249	22000	0.4863
0.8754	2.3777	22500	0.4859
0.8645	2.4306	23000	0.4852
0.8500	2.4834	23500	0.4841
0.8699	2.5362	24000	0.4842
0.8449	2.5891	24500	0.4841
0.8593	2.6419	25000	0.4841
0.7919	2.6948	25500	0.4837
0.7707	2.7476	26000	0.4841
0.8306	2.8005	26500	0.4839
0.7969	2.8533	27000	0.4837
0.9231	2.9061	27500	0.4837
0.9109	2.9590	28000	0.4836

Framework versions

PEFT 0.18.1
Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 114

Model tree for AhmedZaky1/authorship_model

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Adapter

(1007)

this model