Nexesenex/Llama_3.x_70b_SmarTricks_0.41_R1

abouts

Functionnal merge of Fallen Llama R1 involving Nemotron, and Hitachi FLDx2 instead of Tulu. Brick for ulterior merge within the SmarTricks series, but works well as a standalone also. Moderately uncensored.

---

benchs

PPL Wikitext 512 ENG : 3.19 ; ARC-C : 61.85 ; ARC-E : 82.45.

---

merge

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 TheDrummer/Fallen-Llama-3.3-R1-70B-v1 as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
• hitachi-nlp/Llama-3.1-70B-FLDx2

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: hitachi-nlp/Llama-3.1-70B-FLDx2
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
    parameters:
      weight: 1.0
base_model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union