metadata
base_model:
- microsoft/NextCoder-7B
- nvidia/OpenCodeReasoning-Nemotron-7B
- Qwen/Qwen2.5-7B
- Qwen/Qwen2.5-Coder-7B
library_name: transformers
tags:
- mergekit
- merge
datasets:
- bigcode/commitpackft
- microsoft/NextCoderDataset-Conversational
- bigcode/starcoderdata
- nvidia/OpenCodeReasoning
Next_Nemotron_Reasoning_Coder-7B
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
- nvidia-OpenCodeReasoning-Nemotron-7B
- microsoft-NextCoder-7B
Configuration
The following YAML configuration was used to produce this model:
base_model: C:/Users/GSS1147/Desktop/nvidia-OpenCodeReasoning-Nemotron-7B
dtype: float16
merge_method: slerp
parameters:
t:
- filter: embed_tokens
value: 0.0
- filter: self_attn
value: 0.5
- filter: mlp
value: 0.5
- filter: lm_head
value: 1.0
- value: 0.5
slices:
- sources:
- layer_range:
- 0
- 28
model: C:/Users/GSS1147/Desktop/nvidia-OpenCodeReasoning-Nemotron-7B
- layer_range:
- 0
- 28
model: C:/Users/GSS1147/Desktop/microsoft-NextCoder-7B