VyoJ/Qwen2.5-Coder-1.5B-Instruct-be-GGUF

Model Information

Qwen2.5-Coder-1.5B-Instruct is a code-generation tuned LLM from the Qwen series of models. It was converted to GGUF formats by QuantFactory.

I converted it to a big-endian format and uploaded for use on IBM z/OS machines.

Model developer: Qwen (Alibaba Cloud)

Model Architecture: Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings

License: Use of Qwen2.5-Coder-1.5B-Instruct is governed by the Apache 2.0 License.

For more details on the model, please go to Qwen's original model card