14 lines
830 B
Markdown
14 lines
830 B
Markdown
|
---
|
||
|
|
pipeline_tag: image-text-to-text
|
||
|
|
base_model:
|
||
|
|
- huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated
|
||
|
|
---
|
||
|
|
These are quantizations of the model [Huihui-Qwen3-VL-2B-Instruct-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated).
|
||
|
|
|
||
|
|
These quantizations were created using an imatrix merged from [combined\_all\_large](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_large.parquet) and [harmful.txt](https://github.com/Sumandora/remove-refusals-with-transformers) to leverage the abliterated nature of the model.
|
||
|
|
|
||
|
|
**Usage Notes:**
|
||
|
|
- Download the latest [llama.cpp](https://github.com/ggml-org/llama.cpp) to use these quantizations.
|
||
|
|
- Try to use the best quality you can run.
|
||
|
|
- For the `mmproj` file, the F32 version is recommended for best results (F32 > BF16 > F16).
|