Axilotal/cadquery-qwen2.5-7b-v5

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Axilotal/cadquery-qwen2.5-7b-v5 is a 7.6 billion parameter Qwen2.5-Coder-7B-Instruct-bnb-4bit model, developed by Axilotal. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for instruction-following tasks, leveraging its base as a coder model.

Loading preview...

Model Overview

Axilotal/cadquery-qwen2.5-7b-v5 is a 7.6 billion parameter language model developed by Axilotal. It is a finetuned version of the unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit base model, indicating its foundation in code-centric instruction following. The finetuning process utilized Unsloth and Huggingface's TRL library, which facilitated a 2x acceleration in training speed.

Key Characteristics

  • Base Model: Finetuned from unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit, suggesting capabilities inherited from a coder-focused architecture.
  • Training Efficiency: Leverages Unsloth for significantly faster training, which can imply more iterative development or specialized finetuning.
  • Parameter Count: Operates with 7.6 billion parameters, placing it in the medium-sized category for LLMs.
  • Context Length: Supports a context length of 32768 tokens.

Potential Use Cases

  • Instruction Following: Suitable for tasks requiring the model to adhere to specific instructions, particularly those related to its coder base.
  • Code-Related Applications: Given its origin from a "Coder" model, it may perform well in tasks like code generation, completion, or explanation.
  • Research and Development: Its efficient training methodology makes it a candidate for further experimentation and finetuning for specific domain applications.