Novaciano/IN-EVALUATION-6

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 xdrshjr/llama3.2_1b_uncensored_5000_8epoch_lora as a base.

Models Merged

The following models were included in the merge:

• suayptalha/FastLlama-3.2-1B-Instruct
• neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8
• DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1
• Weyaxi/Einstein-v8-Llama3.2-1B

Configuration

The following YAML configuration was used to produce this model:

base_model: xdrshjr/llama3.2_1b_uncensored_5000_8epoch_lora
merge_method: model_stock
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]
models:
- model: suayptalha/FastLlama-3.2-1B-Instruct

- model: neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8
- model: Weyaxi/Einstein-v8-Llama3.2-1B


- model: DeepAutoAI/Explore_Llama-3.2-1B-Inst_v1.1