SanjiWatsuki's picture
Upload folder using huggingface_hub
a24af6d verified
metadata
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:

🧩 Configuration

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: [""]