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)