Avg. Total Time
32.76s
Avg. TTFT
31.39s
Avg. Prefill TPS
0.51
Avg. Gen TPS
19.02
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
2/3/2025
base_model:
While I was trying a new merge method for my Tarek07/Progenitor-V1.2-LLaMa-70B model, I noticed a substantial increase in the models proclivity for more NSFW themes. I then had the idea to try and merge the most 'nsfw' models I know in the same way and see how it turns out. Still Testing.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCE merge method using nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
# Pivot model
- model: SicariusSicariiStuff/Negative_LLAMA_70B
# Target models
- model: NeverSleep/Lumimaid-v0.2-70B
- model: Sao10K/L3.1-70B-Hanami-x1
- model: Sao10K/70B-L3.3-mhnnn-x1
- model: Nohobby/L3.3-Prikol-70B-v0.3
merge_method: sce
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
parameters:
select_topk: 1.0
dtype: bfloat16