Deepseek-EVA-32B-DELLA-v1 / mergekit_config.yml
Downtown-Case's picture
Upload folder using huggingface_hub
5dcc510 verified
raw
history blame contribute delete
556 Bytes
models:
- model: /home/alpha/Models/Raw/Qwen_Qwen2.5-32B
# No parameters necessary for base model
- model: /home/alpha/Models/Raw/nbeerbower_EVA-Gutenberg3-Qwen2.5-32B
parameters:
weight: 0.5
density: 0.5
- model: /home/alpha/Models/Raw/deepseek-ai_DeepSeek-R1-Distill-Qwen-32B
parameters:
weight: 0.5
density: 0.7
merge_method: della
tokenizer:
source: "union"
base_model: /home/alpha/Models/Raw/Qwen_Qwen2.5-32B
chat_template: "deepseek"
parameters:
int8_mask: true
epsilon: 0.17
lambda: 1
dtype: bfloat16