base_model, datasets, language, library_name, license, tags
| base_model | datasets | language | library_name | license | tags | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|
|
transformers | apache-2.0 |
|
🚣 Styx 12B
A saved prototype of an earlier merge test, made before Savage Sands.
This model uses pre-ablated components and may have some refusals.
architecture: MistralForCausalLM
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
models:
- model: B:/12B/Sorihon--Geodesic-Phantom-12B-Heretic
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
- model: B:/12B/Sorihon--Nether-Moon-12B-Heretic
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
- model: B:/12B/IIEleven11--Kalypso
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
- model: B:/12B/EldritchLabs--Human-Like-Mistral-Nemo-Instruct-2407-MPOA
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
- model: B:/12B/EldritchLabs--MN-12B-RP-Ink-Longform-MPOA
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
- model: B:/12B/MuXodious-Rocinante-X-12B-v1-absolute-heresy
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
- model: B:/12B/PocketDoc--Dans-DangerousWinds-V1.1.0-12b
parameters:
weight: 0.3
density: 0.9
epsilon: 0.09
merge_method: della
parameters:
lambda: 1.0
normalize: false
int8_mask: false
rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: B:/12B/Sorihon--Geodesic-Phantom-12B-Heretic