Downloads · 30 days
50
12% of all-time downloads
Qwen2.5-VL-7B-Instruct-abliterated-nvfp4
ApacheOne/Qwen2.5-VL-7B-Instruct-abliterated-nvfp4
Qwen2.5-VL-7B-Instruct-abliterated-nvfp4 is a machine learning model from ApacheOne. 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 apache-2.0.
- Qwen25VL7Bnvfp4fixedBF16.safetensors - Replaced uint8 (152064, 1792) (lmhead.weight)lmhead and (model.embedtokens.weight)nn.Embedding with BF16 (152064, 3584). works in comfy
All-time downloads
403
Public
Repo size
72.5 GB
Likes
6
Public
Repo makeup
Click a slice to open those files.
.safetensors50.6 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Feb 23, 2026
- Updated
- Feb 24, 2026
- SHA
- 70c4950d
Base models
Model card
From the Hugging Face model README
Combined NVFP4 Encoder
Qwen25VL7B_nvfp4_fixedBF16.safetensors- Replaced uint8 (152064, 1792) (lm_head.weight)lm_head and (model.embed_tokens.weight)nn.Embedding with BF16 (152064, 3584). works in comfy
note: Havent done in depth testing
Qwen25VL7B_nvfp4_simple_raw.safetensors- has uint8 (152064, 1792) (lm_head.weight)lm_head and (model.embed_tokens.weight)nn.Embedding. comfy wont load this
Split NVFP4 Encoders
- has uint8 (152064, 1792) lm_head and nn.Embedding. comfy wont load these
split_files/text_encoders/qwen_2.5_vl_7b_text_nvfp4_simple.safetensors- Text encodersplit_files/vision_encoders/qwen_2.5_vl_7b_vision_nvfp4_simple.safetensors- Vision encoder
note: Still working on mixed layers but
- Type
- qwen2_5_vl
- License
- apache-2.0
- Languages
- en
- Created
- Feb 23, 2026
- Updated
- Feb 24, 2026