base_model: rinna/llama-3-youko-8b
gate_mode: random # "hidden", "cheap_embed", "random" の中から選択
dtype: bfloat16
experts_per_token: 2 # 各トークンに対してアクティブなエキスパートの数
experts:
- source_model: aixsatoshi/Llama-3-youko-8b-instruct-chatvector
- source_model: elyza/Llama-3-ELYZA-JP-8B
- Downloads last month
- 15
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.