You can deploy this model and start earning money today!

ndkcjodmsn/
qwen25-32b-instruct-awq-128k

Name: qwen25-32b-instruct-awq-128k
Availability: InStock

Views

No views yet

Qwen2.5-32B-Instruct-AWQ-128k

Identical to Qwen/Qwen2.5-32B-Instruct-AWQ but with YaRN rope scaling baked into config.json for native 128k context.

Weights are loaded from the original repo via safetensors pointers — this repo only overrides config.json and tokenizer files.

max_position_embeddings: 32768 → 131072
Added rope_scaling: {"type": "yarn", "factor": 4.0, "original_max_position_embeddings": 32768}