samairtimer/gemma-3-270m-it-blr-slang

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Aug 31, 2025Architecture:Transformer0.0K Featherless Exclusive Cold

The samairtimer/gemma-3-270m-it-blr-slang model is a 0.3 billion parameter instruction-tuned language model, fine-tuned from google/gemma-3-270m-it. Developed by samairtimer, this model leverages a 32768 token context length and was trained using SFT with the TRL framework. It is designed for text generation tasks, building upon the Gemma architecture for efficient performance.

Loading preview...

Model Overview

The samairtimer/gemma-3-270m-it-blr-slang is a compact, instruction-tuned language model with 0.3 billion parameters, derived from the google/gemma-3-270m-it base model. It was fine-tuned using the SFT (Supervised Fine-Tuning) method within the TRL framework, indicating a focus on adapting its responses to specific instruction-following tasks.

Key Capabilities

  • Instruction Following: As an instruction-tuned model, it is designed to generate responses based on given prompts and instructions.
  • Text Generation: Capable of generating coherent and contextually relevant text, demonstrated by its quick start example for answering open-ended questions.
  • Efficient Performance: With 0.3 billion parameters, it offers a balance between capability and computational efficiency, making it suitable for applications where resource constraints are a consideration.
  • Extended Context Window: Features a 32768 token context length, allowing it to process and generate text based on longer input sequences.

Training Details

This model was trained using the SFT method, which typically involves fine-tuning on a dataset of instruction-response pairs to enhance its ability to follow user commands. The training utilized specific versions of popular machine learning frameworks:

  • TRL: 0.23.0
  • Transformers: 4.56.1
  • Pytorch: 2.8.0+cu126
  • Datasets: 4.0.0
  • Tokenizers: 0.22.0

Good For

  • Quick Prototyping: Its smaller size allows for faster experimentation and deployment.
  • Instruction-based Applications: Ideal for tasks requiring the model to adhere to specific instructions or formats.
  • Resource-constrained Environments: Suitable for deployment on hardware with limited computational resources.

Finetunes
1 models