mira1eval/Threen-V0.7
VISIONConcurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 8, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
mira1eval/Threen-V0.7 is a 9 billion parameter instruction-tuned causal language model developed by mira1eval, finetuned from unsloth/Qwen3.5-9B. This model was optimized for faster training using Unsloth and Huggingface's TRL library, making it efficient for various natural language processing tasks. With a 32768 token context length, it is suitable for applications requiring extensive context understanding and generation.
Loading preview...
mira1eval/Threen-V0.7: An Efficiently Finetuned Qwen3.5-9B Model
mira1eval/Threen-V0.7 is a 9 billion parameter language model, finetuned by mira1eval from the unsloth/Qwen3.5-9B base model. This iteration focuses on training efficiency, leveraging Unsloth and Huggingface's TRL library to achieve a 2x faster training process.
Key Capabilities & Features
- Efficient Training: Benefits from Unsloth's optimizations, allowing for quicker fine-tuning cycles.
- Qwen3.5 Architecture: Built upon the robust Qwen3.5 foundation, inheriting its general language understanding and generation capabilities.
- Instruction-Tuned: Designed to follow instructions effectively, making it versatile for various NLP applications.
- Extended Context Window: Supports a context length of 32768 tokens, enabling the processing of longer inputs and generating more coherent, extended responses.
Good For
- Rapid Prototyping: Ideal for developers looking to quickly fine-tune a powerful 9B model for specific tasks.
- General NLP Tasks: Suitable for a wide range of applications including text generation, summarization, question answering, and conversational AI.
- Resource-Efficient Development: Offers a balance of performance and training efficiency, making it accessible for projects with moderate computational resources.
- Applications Requiring Long Context: Its 32768 token context window is beneficial for tasks that demand understanding and generating text over extended passages.