Jellon/Qwen2.5-14B-Infermatic-Crea-v2-exl2-6bpw-h8

6bpw exl2 quant of: https://huggingface.co/Infermatic/14b-Qwen2.5-Infermatic-Crea-v2

---

14b-Qwen2.5-Infermatic-Crea-v2

This was made thanks to infermatic.ai

This version is slightly more uncensored than the V1, both are good at describing things (like feelings, places, objects, situations and so on)

RP/Story writing

Probably will release soon new recommended settings for this model on the settings archive on Infermatic.ai

pd. if you have refusals it can be fixed with good settings and prompts (or probably with a swipe)

Any feedback can be shared on our discord server

This is a merge of pre-trained language models created using mergekit.

---

Merge Details

Merge Method

This model was merged using the Model Stock merge method using huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2 as a base.

Models Merged

The following models were included in the merge:

• Sao10K/14B-Qwen2.5-Kunou-v1
• v000000/Qwen2.5-Lumen-14B
• v000000/Qwen2.5-14B-Gutenberg-1e-Delta

Configuration

The following YAML configuration was used to produce this model:

name:                Qwen2.5-14B-Infermatic-crea
merge_method:        model_stock
base_model:          huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
tokenizer_source:    base
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           v000000/Qwen2.5-Lumen-14B
  - model:           v000000/Qwen2.5-14B-Gutenberg-1e-Delta
  - model:           Sao10K/14B-Qwen2.5-Kunou-v1
dtype:               bfloat16
out_dtype:           bfloat16