README.md

metadata

base_model:
  - Nexusflow/Starling-LM-7B-beta
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
  - jan-hq/trinity-v1
  - udkai/Garrulus
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.5
  - cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.2
  - Contamination/contaminated_proof_7b_v1.0_safetensor
library_name: transformers
tags:
  - mergekit
  - merge
license: cc-by-nc-nd-4.0

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using cognitivecomputations/dolphin-2.9.3-mistral-7B-32k as a base.

Models Merged

The following models were included in the merge:

• Nexusflow/Starling-LM-7B-beta
• EmbeddedLLM/Mistral-7B-Merge-14-v0.1
• jan-hq/trinity-v1
• udkai/Garrulus
• EmbeddedLLM/Mistral-7B-Merge-14-v0.5
• EmbeddedLLM/Mistral-7B-Merge-14-v0.2
• Contamination/contaminated_proof_7b_v1.0_safetensor

Configuration

The following YAML configuration was used to produce this model:

base_model: cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
dtype: bfloat16
merge_method: model_stock
models:
  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
  - model: Contamination/contaminated_proof_7b_v1.0_safetensor
  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
  - model: udkai/Garrulus
  - model: Nexusflow/Starling-LM-7B-beta
  - model: jan-hq/trinity-v1
  - model: cognitivecomputations/dolphin-2.9.3-mistral-7B-32k