wanlige/li-14b-1m-model-stoke

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 Qwen/Qwen2.5-14B-Instruct-1M as a base.

Models Merged

The following models were included in the merge:

• Azure99/Blossom-V6-14B
• Qwen/Qwen2.5-14B
• Qwen/Qwen2.5-Coder-14B-Instruct
• Qwen/Qwen2.5-14B-Instruct
• EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
• arcee-ai/Virtuoso-Small-v2
• tanliboy/lambda-qwen2.5-14b-dpo-test

Configuration

The following YAML configuration was used to produce this model:

name:                li-14b-1m-model-stoke
merge_method:        model_stock
base_model:          Qwen/Qwen2.5-14B-Instruct-1M
tokenizer_source:    base
dtype:               float32
out_dtype:           bfloat16
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           Qwen/Qwen2.5-Coder-14B-Instruct
  - model:           tanliboy/lambda-qwen2.5-14b-dpo-test
  - model:           Qwen/Qwen2.5-14B-Instruct
  - model:           EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
  - model:           arcee-ai/Virtuoso-Small-v2
  - model:           Azure99/Blossom-V6-14B
  - model:           Qwen/Qwen2.5-14B