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

Libraries

How to use youssefedweqd/working with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use youssefedweqd/working with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/youssefedweqd/working

SGLang

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

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

working / Model /LLaMA-Factory /examples /train_lora /QA.yaml

youssefedweqd

Training in progress, step 1500

80a845c verified 11 months ago

raw

history blame contribute delete

958 Bytes


	### model
	model_name_or_path: Qwen/Qwen2.5-1.5B
	trust_remote_code: true

	### method
	stage: sft
	do_train: true
	finetuning_type: lora
	lora_rank: 64
	lora_target: all

	### dataset
	dataset: QAtrain
	eval_dataset: QAval
	template: qwen
	cutoff_len: 2048
	# max_samples: 50
	overwrite_cache: true
	preprocessing_num_workers: 8

	### output
	resume_from_checkpoint: /kaggle/working/Model/last-checkpoint
	output_dir: /kaggle/working/
	logging_steps: 50
	save_steps: 200
	plot_loss: true
	overwrite_output_dir: true

	### train
	per_device_train_batch_size: 1
	gradient_accumulation_steps: 16
	learning_rate: 1.0e-4
	num_train_epochs: 3.0
	lr_scheduler_type: cosine
	warmup_ratio: 0.1
	bf16: true # full
	ddp_timeout: 180000000
	torch_compile: false
	### eval
	# val_size: 0.1
	per_device_eval_batch_size: 1
	eval_strategy: steps
	eval_steps: 200

	report_to: wandb
	run_name: Qwennn

	push_to_hub: true
	export_hub_model_id: Youssef/QWEN_Arabic_Q&A
	hub_private_repo: true
	hub_strategy: checkpoint