Mistral-Small24B-sce-merge-v1

Mistral-Small24B-sce-merge-v1 is a merge of the following models using mergekit:

🧩 Configuration

merge_method: sce
models:
  - model: trashpanda-org/MS-24B-Mullein-v0
  - model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
  - model: cognitivecomputations/Dolphin3.0-Mistral-24B
  - model: unsloth/Mistral-Small-24B-Instruct-2501
base_model: cognitivecomputations/Dolphin3.0-Mistral-24B
tokenizer:
  source: base
parameters:
  select_topk: 0.95
  int8_mask: true
dtype: float32
out_dtype: bfloat16
normalize: true
Downloads last month
11
Safetensors
Model size
23.6B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.