Add Q4_KM GGUF, config, and tokenizer files

75d35a1 verified 18 days ago

385 Bytes

metadata

tags:
  - qwen
  - qwen2_5
  - gguf
  - text-generation
  - quantization
model_name: Qwen2.5 Coder 7B Instruct - Q4_KM (Consolidated)

Qwen2.5 Coder 7B Instruct – Q4_KM (Consolidated)

Source: Qwen/Qwen2.5-Coder-7B-Instruct-GGUF

This repo bundles the Q4_KM GGUF variant along with necessary configuration and tokenizer files. No weight merging. Compatible with llama.cpp ecosystem.