Edit model card

Refer to the original models for best usage.


Mergekit Recipe

# Mistral Merging
merge_method: linear
dtype: float16
models:
  - model: KoboldAI/Mistral-7B-Holodeck-1
    parameters:
      weight: 1.0
  - model: KoboldAI/Mistral-7B-Erebus-v3
    parameters:
      weight: 1.0
name: MV01-Holodeck-Erebus-7B
---

# Mistral Stacking
merge_method: passthrough
dtype: float16
slices:
  - sources:
    - model: MV01-Holodeck-Erebus-7B
      layer_range: [0, 24]
  - sources:
    - model: MV01-Holodeck-Erebus-7B
      layer_range: [8, 32]
name: MV01-Stacked-Holodeck-Erebus-Unhealed-10.7B
---

# Mistral Stack Healing
merge_method: task_arithmetic
dtype: float16
base_model: Undi95/Mistral-11B-v0.1
models:
  - model: Sao10K/Fimbulvetr-11B-v2
    parameters:
      weight: 1.0
  - model: MV01-Stacked-Holodeck-Erebus-Unhealed-10.7B
    parameters:
      weight: 1.0
Downloads last month
12
GGUF
Model size
10.7B params
Architecture
llama

4-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for PJMixers/Fimbulvetr-Holodeck-Erebus-10.7B-GGUF