mimi94/subway-assistant-v1

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Aug 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

mimi94/subway-assistant-v1 is a 7 billion parameter Mistral-based instruction-tuned causal language model developed by mimi94. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general instruction-following tasks, leveraging its Mistral architecture and 4096-token context length.

Loading preview...

Model Overview

mimi94/subway-assistant-v1 is a 7 billion parameter instruction-tuned model based on the Mistral architecture. Developed by mimi94, this model was fine-tuned using the Unsloth library, which facilitated a 2x faster training process, alongside Huggingface's TRL library. It operates with a context length of 4096 tokens.

Key Characteristics

  • Architecture: Mistral-7B-Instruct-v0.2 base model.
  • Training Efficiency: Utilizes Unsloth for accelerated fine-tuning.
  • Parameter Count: 7 billion parameters.
  • Context Length: Supports up to 4096 tokens.

Intended Use Cases

This model is suitable for general instruction-following applications where a 7B parameter model with efficient training methods is beneficial. Its foundation on Mistral-7B-Instruct-v0.2 suggests capabilities in understanding and generating human-like text based on given prompts.