TuralBayev/axeron-forge-d2012984
TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 8, 2026Architecture:Transformer Featherless Exclusive Cold
DeLabs/axeron-forge-d2012984 is a 7.6 billion parameter language model forged using the Task Arithmetic method, based on Qwen/Qwen2.5-7B. This model integrates the capabilities of Qwen/Qwen2.5-7B-Instruct, making it suitable for instruction-following tasks. It leverages a specific layer-slicing configuration to combine the base and instruction-tuned versions of the Qwen2.5-7B family.
Loading preview...
Overview
DeLabs/axeron-forge-d2012984 is a 7.6 billion parameter language model created using the forgelm framework. It employs the Task Arithmetic forge method, which combines the weights of different pre-trained models to create a new, specialized model. The base model for this forge is Qwen/Qwen2.5-7B, a robust foundation model.
Key Capabilities
- Instruction Following: This model integrates the instruction-tuned capabilities of Qwen/Qwen2.5-7B-Instruct, making it proficient in understanding and executing user commands and prompts.
- Model Blending: Utilizes a specific configuration to blend the base Qwen2.5-7B model with its instruction-tuned variant, potentially offering a balance between general knowledge and instruction adherence.
- Qwen2.5 Architecture: Benefits from the underlying architecture and training of the Qwen2.5-7B series, known for its strong performance across various language tasks.
Good For
- Instruction-tuned applications: Ideal for scenarios requiring the model to follow specific instructions or respond in a structured manner.
- Experimentation with forged models: Developers interested in exploring models created via the Task Arithmetic method and the
forgelmframework. - Leveraging Qwen2.5 capabilities: Projects that can benefit from the performance characteristics of the Qwen2.5-7B family, with an added instruction-following layer.