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

Libraries

How to use Ekanari/SLM_LAW with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ekanari/SLM_LAW")
model = AutoModelForCausalLM.from_pretrained("Ekanari/SLM_LAW")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ekanari/SLM_LAW with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ekanari/SLM_LAW

SGLang

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

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

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

SLM_LAW

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the arrow dataset. It achieves the following results on the evaluation set:

Loss: 1.1380

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: 0.0005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 1000
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss
1.5039	0.0248	500	1.4864
1.4341	0.0496	1000	1.4603
1.3489	0.0744	1500	1.3271
1.2564	0.0992	2000	1.2632
1.2071	0.1240	2500	1.2287
1.1771	0.1488	3000	1.2031
1.1565	0.1737	3500	1.1845
1.1338	0.1985	4000	1.1688
1.1158	0.2233	4500	1.1507
1.0999	0.2481	5000	1.1380

Framework versions

Transformers 4.52.0.dev0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.0

Downloads last month: -

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for Ekanari/SLM_LAW

Base model

Qwen/Qwen2.5-0.5B

Finetuned

(606)

this model