djpartyface/colosso-sn47-evolai-qwen25-15b

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 11, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The djpartyface/colosso-sn47-evolai-qwen25-15b is a 1.5 billion parameter language model based on the Qwen2.5 architecture. It is a merged model, specifically created for the SN47 EvolAI miner bootstrap. This model was produced by merging a local SBE LoRA adapter, `evolai-qwen25-15b-lora-acceptance-20260605T103709`, into the base `Qwen/Qwen2.5-1.5B` model, indicating a specialized fine-tuning for a particular application.

Loading preview...

Model Overview

The djpartyface/colosso-sn47-evolai-qwen25-15b is a specialized 1.5 billion parameter language model built upon the Qwen2.5 architecture. It was developed by djpartyface as a merged model, specifically intended for the SN47 EvolAI miner bootstrap.

Key Characteristics

  • Architecture: Based on the robust Qwen2.5 model family.
  • Parameter Count: Features 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Origin: This model is the result of merging a local SBE LoRA adapter, evolai-qwen25-15b-lora-acceptance-20260605T103709, with the foundational Qwen/Qwen2.5-1.5B model.
  • Training Details: The merging process involved training over 512 rows and 9000 steps, demonstrating a significant reduction in loss from 3.8946 to 0.2176, and successfully passed a quality gate.

Intended Use Case

This model is explicitly designed and optimized for the SN47 EvolAI miner bootstrap, suggesting a highly specialized application within a specific technical or operational context. Its fine-tuning indicates suitability for tasks related to its intended purpose, likely involving data processing, control, or specific language generation relevant to the EvolAI miner system.

Finetunes
2 models