README.md

---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- deepseek-ai/deepseek-llm-7b-base
---

# Breeze-13B-32k-Base-v1_0

Breeze-13B-32k-Base-v1_0 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)

## 🧩 Configuration

```yaml
dtype: bfloat16
merge_method: linear
slices:
- sources:
  - layer_range: [0, 8]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [0, 8]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
- sources:
  - layer_range: [4, 12]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [4, 12]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
- sources:
  - layer_range: [8, 16]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [8, 16]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
- sources:
  - layer_range: [12, 20]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [12, 20]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
- sources:
  - layer_range: [16, 24]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [16, 24]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
- sources:
  - layer_range: [20, 28]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [20, 28]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
- sources:
  - layer_range: [24, 32]
    model: deepseek-ai/deepseek-llm-7b-base
  - layer_range: [24, 32]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      weight: 0
tokenizer_source: union

```