NEXS-deepseek-7b-multislerp/README.md

library_name, tags, base_model

library_name	tags	base_model
transformers	mergekit merge multislerp task-vector	deepseek-ai/deepseek-llm-7b-base deepseek-ai/deepseek-math-7b-instruct deepseek-ai/deepseek-coder-7b-instruct-v1.5

NEXS Deepseek-7B Multi-SLERP Merge

A multi-SLERP merge of LlamaForCausalLM domain experts covering math and code, produced with mergekit. Part of the NEXS multi-SLERP merge collection.

Method

Multi-SLERP (multislerp) performs barycentric spherical interpolation on a hypersphere for more than two models: it projects the models into the tangent space at their weighted Euclidean mean, interpolates, and projects back. Here it is run in task-vector space — each source's delta from the shared base model is computed, the deltas are spherically averaged with equal weight (normalize_weights: true, eps: 1e-8), and the result is added back to the base. Merging was done with mergekit.

All variants share an identical vocabulary (102400); no tokenizer reconciliation was needed.

Sources

Base model (task-vector reference): deepseek-ai/deepseek-llm-7b-base

Merged variants (equal weight 1.0 each):

• deepseek-ai/deepseek-math-7b-instruct
• deepseek-ai/deepseek-coder-7b-instruct-v1.5

mergekit config

merge_method: multislerp
base_model: deepseek-ai/deepseek-llm-7b-base
tokenizer_source: base
dtype: float32
out_dtype: bfloat16
parameters:
  normalize_weights: true
  eps: 1.0e-8
models:
  - model: deepseek-ai/deepseek-math-7b-instruct
    parameters: {weight: 1.0}
  - model: deepseek-ai/deepseek-coder-7b-instruct-v1.5
    parameters: {weight: 1.0}