Edit model card

Merge Details

This experimental model is the result of TIES merging only on the embedding weights, with Qwen/Qwen1.5-1.8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: ties
base_model: Qwen/Qwen1.5-1.8B
models:
  - model: aloobun/Reyna-Mini-1.8B-v0.2
    parameters:
      weight: 0.7 
      density:
        - filter: embed_tokens 
          value: 0.66          
        - value: 1.0
  - model: aloobun/Reyna-Mini-1.8B-v0.1
    parameters:
      weight: 
        - filter: embed_tokens
          value: 0.3 
        - value: 0.0 
      density: 0.66
Downloads last month
2,692
Safetensors
Model size
1.84B params
Tensor type
BF16
·

Merge of

Collection including aloobun/Synch-Qwen1.5-1.8B