H34v7 - Models Merge and Collections GGUF/i1-GGUF
Collection
3 items
โข
Updated
This is a merge of pre-trained language models created using mergekit.
ollama run hf.co/h34v7/DansXPantheon-RP-Engine-V1.0-24b-Small-Instruct-old-GGUF:Q4_K_M
This model was merged using the SCE merge method using unsloth/Mistral-Small-24B-Base-2501 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: unsloth/Mistral-Small-24B-Base-2501
merge_method: sce
dype: float32
out_dtype: bfloat16
tokenizer:
source: unsloth/Mistral-Small-24B-Instruct-2501
models:
- model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
parameters:
select_topk: 0.5
- model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
parameters:
select_topk: 0.5
4-bit