EVA-Tissint-14B

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

Combining Tissint with EVA v0.2 seemed to yield nice results in RP, I've uploaded the model so others can try it as well.

Recommended samplers are 0.1 Min P, 1.02 Repititon penalty, and DRY's range set to 2048.

If you'd like to use XTC, I recommend a threshold of 0.2. Lower thresholds seem to adversely affect the coherency.

Quantisations

Static: https://huggingface.co/mradermacher/EVA-Tissint-14B-GGUF

Imatrix: https://huggingface.co/mradermacher/EVA-Tissint-14B-i1-GGUF

Merge Method

This model was merged using the della_linear merge method using /home/ciaran/Documents/Quantisingmodels/EVA-Qwen2.5-14B-v0.2/ as a base.

Models Merged

The following models were included in the merge:

• /home/ciaran/Documents/Quantisingmodels/Tissint-14B-128k-RP/

Configuration

The following YAML configuration was used to produce this model:

models:
    - model: /home/ciaran/Documents/Quantisingmodels/Tissint-14B-128k-RP/
      parameters:
        density: 0.4
        weight: 0.3
    - model: /home/ciaran/Documents/Quantisingmodels/EVA-Qwen2.5-14B-v0.2/
      parameters:
        density: 0.6
        weight: 0.7

merge_method: della_linear
base_model: /home/ciaran/Documents/Quantisingmodels/EVA-Qwen2.5-14B-v0.2/
parameters:
    epsilon: 0.05
    lambda: 1
dtype: bfloat16