Hourly Usage
Performance Metrics
Avg. Total Time
6.59s
Avg. TTFT
5.56s
Avg. Prefill TPS
6.48
Avg. Gen TPS
24.13
Model Information
Context Size
32768
Quantization
r64
Engine
aphrodite
Creation Method
Merge
Model Type
Llama70B
Chat Template
Llama 3
Reasoning
No
Vision
No
Parameters
70B
Added At
4/9/2025
thumbnail: >- https://cdn-uploads.huggingface.co/production/uploads/67c10cfba43d7939d60160ff/o9eVw82xaajZx_zCO9qyJ.png language:
- en license: llama3.3 license_name: llama3.3 license_link: https://github.com/facebookresearch/llama/blob/main/LICENSE inference: false tags:
- nsfw
- explicit
- roleplay
- Furry base_model:
- Steelskull/L3.3-Cu-Mai-R1-70b
Wanton-Wolf-70B
User Discretion Advised
A furry finetune model based on L3.3-Cu-Mai-R1-70b, chosen for its exceptional features. *Tail swish*
✧ Quantized Formats
- GGUF Collection::
✧ Recommended Settings
- Static Temperature: 1.0-1.05
- Min P: 0.02
- DRY Settings (optional):
- Multiplier: 0.8
- Base: 1.75
- Length: 4
✧ Recommended Templates
The following templates are recommended from the original Cu-Mai model page, Adjust if needed:
LLam@ception by @.konnect
LeCeption by @Steel - A completely revamped XML version of Llam@ception 1.5.2 with stepped thinking and reasoning
LeCeption Reasoning Configuration:
Start Reply With:
'<think> OK, as an objective, detached narrative analyst, let's think this through carefully:'
Reasoning Formatting (no spaces):
- Prefix:
'<think>' - Suffix:
'</think>'
✧ Credits
Model Author
Original Model Creator
- @SteelSkull - Creator of the L3.3-Cu-Mai-R1-70b base model
Contributors ✨
- @ArtusDev - Donator, Tester
- @SaisExperiments - Tester