license: apache-2.0 | |
tags: | |
- merge | |
- mergekit | |
- lazymergekit | |
# DeepSeek-Coder-Instruct-8x1.3b | |
DeepSeek-Coder-Instruct-8x1.3b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
## 🧩 Configuration | |
```yaml | |
base_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
gate_mode: random | |
dtype: bfloat16 | |
experts: | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
- source_model: deepseek-ai/deepseek-coder-1.3b-instruct | |
positive_prompts: [""] | |
``` |