models:
- model: ArliAI/Llama-3.3-70B-ArliAI-RPMax-v2
- model: Sao10K/70B-L3.3-mhnnn-x1
- model: Sao10K/Llama-3.3-70B-Vulpecula-r1
base_model: deepcogito/cogito-v1-preview-llama-70B
merge_method: model_stock
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
source: base
pad_to_multiple_of: 8
- Downloads last month
- 8
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support