LinjunChen123/Protoss-a
LinjunChen123/Protoss-a is a 2 billion parameter causal language model, fine-tuned from the Qwen3-1.7B base model using H2O LLM Studio. This model is designed for general text generation tasks, leveraging its Qwen3 architecture and a 32768-token context length. It is suitable for applications requiring conversational AI and text completion, built upon a robust transformer framework.
Loading preview...
Model Overview
LinjunChen123/Protoss-a is a 2 billion parameter causal language model, developed by fine-tuning the Qwen/Qwen3-1.7B base model. The training process utilized H2O LLM Studio, a platform for developing large language models. This model features a Qwen3ForCausalLM architecture, including 28 decoder layers and a 32768-token context length, making it capable of handling substantial input sequences.
Key Capabilities
- General Text Generation: Capable of generating human-like text based on provided prompts.
- Conversational AI: Designed to engage in multi-turn conversations, as demonstrated by its usage examples.
- Flexible Deployment: Supports loading with
transformerslibrary, including options fortorch_dtype="auto"anddevice_mapfor GPU utilization. - Quantization Support: Can be loaded in 8-bit or 4-bit quantization for reduced memory footprint, and supports sharding across multiple GPUs.
Good For
- Developers: Those looking for a Qwen3-based model for text generation and conversational applications.
- Experimentation: Users interested in exploring models fine-tuned with H2O LLM Studio.
- Resource-Efficient Deployment: Suitable for environments where quantization and multi-GPU sharding are beneficial for performance and memory management.