Novaciano/Imp-3.2-1B

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:

• Mattia2700/Llama-3.2-1B_AllDataSources_5e-05_constant_512_flattening
• bunnycore/FuseChat-3.2-1B-Creative-RP
• petkopetkov/Llama-3.2-1B-med-diagnosis
• nguyenthetuyen/llama3.1-1B-medical
• AnteriorAI/llama-3-2-1b
• orange67/merged-llama-3.2-1b
• bluetree99/llama-3.2-1B-test
• alpindale/Llama-3.2-1B-Instruct
• kenken6696/Llama-3.2-1B_3_mix_position_understood_unfamiliar
• slchangtw/LLMTwin-Llama-3.2-1B
• deqing/llama_3.2_1b_openwebtext_2025_03_02_converted_fne_gsm8k_2025_03_11

Configuration

The following YAML configuration was used to produce this model:

models:
- model: deqing/llama_3.2_1b_openwebtext_2025_03_02_converted_fne_gsm8k_2025_03_11
- model: orange67/merged-llama-3.2-1b
- model: AnteriorAI/llama-3-2-1b
- model: bluetree99/llama-3.2-1B-test
- model: kenken6696/Llama-3.2-1B_3_mix_position_understood_unfamiliar
- model: petkopetkov/Llama-3.2-1B-med-diagnosis
- model: slchangtw/LLMTwin-Llama-3.2-1B
- model: Mattia2700/Llama-3.2-1B_AllDataSources_5e-05_constant_512_flattening
- model: bunnycore/FuseChat-3.2-1B-Creative-RP
- model: nguyenthetuyen/llama3.1-1B-medical
- model: alpindale/Llama-3.2-1B-Instruct
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]