merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method using meta-llama/Llama-3.2-3B as a base.
Models Merged
The following models were included in the merge:
- Bllossom/llama-3.2-Korean-Bllossom-3B
- Qwen/Qwen2.5-3B
- ICEPVP8977/Uncensored_llama_3.2_3b_safetensors
- Qwen/Qwen2.5-3B-Instruct
- chuanli11/Llama-3.2-3B-Instruct-uncensored
- ibm-granite/granite-3b-code-base-2k
- stabilityai/stable-code-3b
- PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
- meta-llama/Llama-3.2-3B-Instruct
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- layer_range: [0, 1]
model: ICEPVP8977/Uncensored_llama_3.2_3b_safetensors
- sources:
- layer_range: [0, 1]
model: meta-llama/Llama-3.2-3B-Instruct
- sources:
- layer_range: [0, 1]
model: meta-llama/Llama-3.2-3B
- sources:
- layer_range: [0, 1]
model: chuanli11/Llama-3.2-3B-Instruct-uncensored
- sources:
- layer_range: [0, 1]
model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
- sources:
- layer_range: [0, 1]
model: Bllossom/llama-3.2-Korean-Bllossom-3B
- sources:
- layer_range: [0, 1]
model: Qwen/Qwen2.5-3B-Instruct
- sources:
- layer_range: [0, 1]
model: Qwen/Qwen2.5-3B
- sources:
- layer_range: [0, 1]
model: stabilityai/stable-code-3b
- sources:
- layer_range: [0, 1]
model: ibm-granite/granite-3b-code-base-2k
merge_method: passthrough
dtype: float16
base_model: meta-llama/Llama-3.2-3B