ja-llama-3-swallow-8b-instruct-v0.1-x-meta-llama-3-8b-instruct-mmot_merge

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

Merge Details

Merge Method

This model was merged using the MMOT-Merge (Memory Optimal Transport) merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
tokenizer:
  source: union
merge_method: mmot_merge
base_model: meta-llama/Meta-Llama-3-8B-Instruct
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct
  parameters: {}
- model: tokyotech-llm/Llama-3-Swallow-8B-Instruct-v0.1
  parameters: {}
parameters:
  align: true
  eps: 0.05
  iters: 30
  gamma: 1.0
  eta: 5.0
  alpha_cap: 0.8
  ot_cap: 512
  group_size: 512
  cpu_align: false
write_readme: README.md