Modelpublic

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

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

1likes32downloads

Model Card

language:

—en license: apache-2.0 tags:
—text-generation
—instruct
—manim
—lora
—gguf datasets:
—ArunKr/verified-data-manim basemodel: HuggingFaceTB/SmolLM-135M-Instruct libraryname: transformers pipeline_tag: text-generation ---

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

python

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

bash

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