- Q6_K GGUF
MN-12B-Stellar-Veil (static Q6_K GGUF)
This model was converted to GGUF format from v000000/MN-12B-Stellar-Veil
using llama.cpp
Refer to the original model card for more details on the model.
MN-12B-Stellar-Veil
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the linear merge method.
Models Merged
The following models were included in the merge:
- Epiculous/Violet_Twilight-v0.1
- Epiculous/Crimson_Dawn-V0.1
- nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
- nbeerbower/mistral-nemo-gutenberg-12B-v2
- TheDrummer/Rocinante-12B-v1.1
- nbeerbower/Stella-mistral-nemo-12B-v2
- Epiculous/Azure_Dusk-v0.1
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Epiculous/Violet_Twilight-v0.1
parameters:
weight: 0.14
- model: TheDrummer/Rocinante-12B-v1.1
parameters:
weight: 0.15
- model: Epiculous/Crimson_Dawn-V0.1
parameters:
weight: 0.125
- model: nbeerbower/mistral-nemo-gutenberg-12B-v2
parameters:
weight: 0.075
- model: Epiculous/Azure_Dusk-v0.1
parameters:
weight: 0.08
- model: nbeerbower/mistral-nemo-gutenberg-12B-v2
parameters:
weight: 0.075
- model: Epiculous/Violet_Twilight-v0.1
parameters:
weight: 0.1
- model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
parameters:
weight: 0.08
- model: TheDrummer/Rocinante-12B-v1.1
parameters:
weight: 0.08
- model: nbeerbower/Stella-mistral-nemo-12B-v2
parameters:
weight: 0.145
merge_method: linear
dtype: bfloat16
Prompt
[INST] System Message [/INST]
[INST] Name: Let's get started. Please respond based on the information and instructions provided above. [/INST]
<s>[INST] Name: What is your favourite condiment? [/INST]
AssistantName: Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s>
[INST] Name: Do you have mayonnaise recipes? [/INST]
- Downloads last month
- 0
Model tree for v000000/MN-12B-Stellar-Veil-Q6_K-GGUF
Base model
v000000/MN-12B-Stellar-Veil
Quantized
this model