ArunKr/SmolLM-135M-Instruct-manim-gguf

SmolLM-135M-Instruct-manim - Fine-tuned

This repository contains three variants of the model:

• LoRA adapters → ArunKr/SmolLM-135M-Instruct-manim-lora
• Merged FP16 weights → ArunKr/SmolLM-135M-Instruct-manim-16bit
• GGUF quantizations → ArunKr/SmolLM-135M-Instruct-manim-gguf

Training

• Base model: HuggingFaceTB/SmolLM-135M-Instruct
• Dataset: generaleoley/manim-codegen
• Method: LoRA fine-tuning with Unsloth

Quantizations

We provide f16, bf16, f32, and q8_0 GGUF files for llama.cpp / Ollama.

Usage Example

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("ArunKr/SmolLM-135M-Instruct-manim-16bit")
model = AutoModelForCausalLM.from_pretrained("ArunKr/SmolLM-135M-Instruct-manim-16bit")
print(model.generate(**tok("Hello", return_tensors="pt")))

Ollama Example

ollama run ArunKr/SmolLM-135M-Instruct-manim-gguf:<file_name>.gguf

www.ollama.com