Instructions to use teamaMohamed115/smollm-360m-code-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teamaMohamed115/smollm-360m-code-lora with Transformers:

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

pipe = pipeline("text-generation", model="teamaMohamed115/smollm-360m-code-lora")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teamaMohamed115/smollm-360m-code-lora")
model = AutoModelForCausalLM.from_pretrained("teamaMohamed115/smollm-360m-code-lora")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use teamaMohamed115/smollm-360m-code-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teamaMohamed115/smollm-360m-code-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teamaMohamed115/smollm-360m-code-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/teamaMohamed115/smollm-360m-code-lora

SGLang

How to use teamaMohamed115/smollm-360m-code-lora 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 "teamaMohamed115/smollm-360m-code-lora" \
    --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": "teamaMohamed115/smollm-360m-code-lora",
		"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 "teamaMohamed115/smollm-360m-code-lora" \
        --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": "teamaMohamed115/smollm-360m-code-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use teamaMohamed115/smollm-360m-code-lora with Docker Model Runner:
```
docker model run hf.co/teamaMohamed115/smollm-360m-code-lora
```

smollm-360m-code-lora

This is a merged fine-tuned version of HuggingFaceTB/SmolLM2-360M using LoRA.

Model Details

Base Model: HuggingFaceTB/SmolLM2-360M
Fine-tuning Method: LoRA (Low-Rank Adaptation) - Merged
Training: Fine-tuned on Python code generation tasks

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "teamaMohamed115/smollm-360m-code-lora"

# Load model (adapter already merged)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

Downloads last month: 6

Safetensors

Model size

0.4B params

Tensor type

F16

Model tree for teamaMohamed115/smollm-360m-code-lora

Base model

HuggingFaceTB/SmolLM2-360M

Finetuned

(101)

this model

teamaMohamed115
/

smollm-360m-code-lora

smollm-360m-code-lora

Model Details

Usage

Model tree for teamaMohamed115/smollm-360m-code-lora

Space using teamaMohamed115/smollm-360m-code-lora 1