L3-Hecate-8B-v1.1
About:
This is a merge of pre-trained language models created using mergekit.
Recommended Samplers:
Temperature - 1.0
TFS - 0.75
Smoothing Factor - 0.3
Smoothing Curve - 1.1
Repetition Penalty - 1.08
Merge Method
This model was merged a series of model stock, followed by ExPO. It uses a mix of roleplay models to improve performance.
Configuration
The following YAML configuration was used to produce this model:
---
# Mopey RP Mix
models:
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/Llama-3-Sunfall-8b-lora
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/Llama-3-8B-Abomination-LORA
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/llama3-8b-hikikomori-v0.4
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/Llama-3-Instruct-LiPPA-LoRA-8B
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/BlueMoon_Llama3
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/Llama3_RP_ORPO_LoRA
- model: failspy/Llama-3-8B-Instruct-MopeyMule+Azazelle/Llama-3-LongStory-LORA
merge_method: model_stock
base_model: failspy/Llama-3-8B-Instruct-MopeyMule
dtype: float32
vocab_type: bpe
name: mopey_rp
---
models:
- model: Nitral-AI/Hathor_Tahsin-L3-8B-v0.85
- model: Sao10K/L3-8B-Tamamo-v1
- model: Sao10K/L3-8B-Niitama-v1
- model: cycy233/L3-base-v2-e3.0
- model: Azazelle/L3-Hecate-8B-v1.0
- model: R136a1/Bungo-L3-8B
- model: Jellywibble/meseca-20062024-c1
- model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
- model: Jellywibble/lora_120k_pref_data_ep2
- model: Nitral-AI/Hathor_Stable-v0.2-L3-8B
- model: mopey_rp
merge_method: model_stock
base_model: NousResearch/Meta-Llama-3-8B-Instruct
dtype: float32
vocab_type: bpe
name: hq_rp
---
# ExPO
models:
- model: hq_rp
parameters:
weight:
- filter: mlp
value: 1.25
- value: 1.1
merge_method: task_arithmetic
base_model: NousResearch/Meta-Llama-3-8B-Instruct
parameters:
normalize: false
dtype: float32
vocab_type: bpe
- Downloads last month
- 30
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.