Downloads · 30 days
16
22% of all-time downloads
qwen25-32b-instruct-awq-128k
ndkcjodmsn/qwen25-32b-instruct-awq-128k
qwen25-32b-instruct-awq-128k is a machine learning model from ndkcjodmsn. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Identical to Qwen/Qwen2.5-32B-Instruct-AWQ but with YaRN rope scaling baked into config.json for native 128k context.
All-time downloads
73
Public
Parameters
32.8B
19.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors19.3 GB · 100%
Parameter types
How the weights are stored.
I3231.2B · 95%
Base models
Model card
From the Hugging Face model README
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.
Config changes
max_position_embeddings: 32768 → 131072- Added
rope_scaling:{"type": "yarn", "factor": 4.0, "original_max_position_embeddings": 32768}
- Type
- qwen2
- License
- other
- Languages
- en
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026