---
base_model: vectionlabs/Maestro1-9B
library_name: transformers
license: apache-2.0
haffner:
  readme_rev: 1
quantized_by: haffner
tags:
- heretic
- multimodal
- vision-language
- reasoning
- thinking
- math
- code
- long-context
- gguf
language:
- en
- it
---
## About

<p align="center">
  <img src="MaestroBannerHeretic.jpg" width="100%">
</p>

<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### tags:  -->
<!-- ### quants:  BF16 Q8\_0 Q6\_K Q5\_1 Q5\_K\_M Q5\_K\_S Q5\_0 Q4\_1 IQ4\_NL IQ4\_XS IQ3\_M IQ3\_S Q3\_K\_S Q3\_K\_M Q3\_K\_L Q2\_K TQ2\_0 TQ1\_0 Q1\_0
<!-- ### quants\_skip:  -->
<!-- ### skip\_mmproj:  -->
Heretic'ed safetensors and GGUF quants of https://huggingface.co/vectionlabs/Maestro1-9B

Multimodal Projector:
- [MMPROJ-BF16 - 1.16GB](https://huggingface.co/haffner/Maestro1-9B-Heretic/resolve/main/Maestro1-9B-heretic-mmproj-BF16.gguf?download=true)
- [MMPROJ-Q8_0 - 752MB](https://huggingface.co/haffner/Maestro1-9B-Heretic/resolve/main/Maestro1-9B-heretic-mmproj-Q8_0.gguf?download=true)

<!-- provided-files -->

Refusals:  3/100, KL divergence: 0.0741

* Parameters:
  * direction_index = 18.77
  * attn.o_proj.max_weight = 1.37
  * attn.o_proj.max_weight_position = 27.86
  * attn.o_proj.min_weight = 1.33
  * attn.o_proj.min_weight_distance = 18.73
  * mlp.down_proj.max_weight = 1.34
  * mlp.down_proj.max_weight_position = 22.02
  * mlp.down_proj.min_weight = 1.24
  * mlp.down_proj.min_weight_distance = 14.79

<!-- end -->