Instructions to use seccret444/cyber_model_TA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use seccret444/cyber_model_TA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "seccret444/cyber_model_TA")

Transformers

How to use seccret444/cyber_model_TA with Transformers:

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

pipe = pipeline("text-generation", model="seccret444/cyber_model_TA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("seccret444/cyber_model_TA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use seccret444/cyber_model_TA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "seccret444/cyber_model_TA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "seccret444/cyber_model_TA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/seccret444/cyber_model_TA

SGLang

How to use seccret444/cyber_model_TA 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 "seccret444/cyber_model_TA" \
    --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": "seccret444/cyber_model_TA",
		"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 "seccret444/cyber_model_TA" \
        --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": "seccret444/cyber_model_TA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use seccret444/cyber_model_TA with Docker Model Runner:
```
docker model run hf.co/seccret444/cyber_model_TA
```

cyber_model_TA / README.md

seccret444

End of training

d506d0a verified 7 months ago

preview code

Raw

History Blame Contribute Delete

2.04 kB

	---
	library_name: peft
	license: apache-2.0
	base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
	tags:
	- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B-Instruct
	- lora
	- transformers
	pipeline_tag: text-generation
	model-index:
	- name: cyber_model_TA
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# cyber_model_TA

	This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.3398

	## 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: 2
	- eval_batch_size: 8
	- seed: 42
	- gradient_accumulation_steps: 4
	- 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: linear
	- num_epochs: 3
	- mixed_precision_training: Native AMP

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 0.6269 \| 0.3339 \| 50 \| 0.5233 \|
	\| 0.4874 \| 0.6678 \| 100 \| 0.4507 \|
	\| 0.5023 \| 1.0 \| 150 \| 0.4133 \|
	\| 0.3874 \| 1.3339 \| 200 \| 0.3949 \|
	\| 0.312 \| 1.6678 \| 250 \| 0.3806 \|
	\| 0.2976 \| 2.0 \| 300 \| 0.3520 \|
	\| 0.2021 \| 2.3339 \| 350 \| 0.3579 \|
	\| 0.2143 \| 2.6678 \| 400 \| 0.3415 \|
	\| 0.2198 \| 3.0 \| 450 \| 0.3398 \|


	### Framework versions

	- PEFT 0.18.1
	- Transformers 4.57.5
	- Pytorch 2.9.1+cu128
	- Datasets 4.4.2
	- Tokenizers 0.22.2