metadata

base_model:
  - Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  - lodrick-the-lafted/Limon-8B
  - jondurbin/bagel-8b-v1.0
  - jeiku/Orthocopter_8B
  - mpasila/Llama-3-LimaRP-Instruct-LoRA-8B
  - cgato/L3-TheSpice-8b-v0.8.3
  - lodrick-the-lafted/Fuselage-8B
  - Nitral-AI/Poppy_Porpoise-0.72-L3-8B
  - Vdr1/L3-8B-Sunfall-Stheno-v3.2
  - Nitral-AI/Poppy_Porpoise-0.72-L3-8B
  - Blackroot/Llama-3-8B-Abomination-LORA
library_name: transformers
tags:
  - mergekit
  - merge
  - llama
  - not-for-all-audiences

🪶Llama-3-8B-Serpentine

RP/Writer Model, big merge, scored well. Smart and less verbose.

Quants

GGUF Q8_0

update: Fixed tokenizer.

-knows when to stop mostly

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Nitral-AI/Poppy_Porpoise-0.72-L3-8B as a base.

Models Merged

The following models were included in the merge:

Credit Edgerunners.

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B+Blackroot/Llama-3-8B-Abomination-LORA
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  - model: cgato/L3-TheSpice-8b-v0.8.3
  - model: Vdr1/L3-8B-Sunfall-Stheno-v3.2
  - model: jondurbin/bagel-8b-v1.0
  - model: lodrick-the-lafted/Fuselage-8B
  - model: lodrick-the-lafted/Limon-8B
  - model: jeiku/Orthocopter_8B+mpasila/Llama-3-LimaRP-Instruct-LoRA-8B
base_model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
merge_method: model_stock
dtype: bfloat16

Prompt Template:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>