RichardErkhov/Chickaboo_-_ChickaQ-V2-Large-Beta-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ChickaQ-V2-Large-Beta - bnb 8bits

• Model creator: https://huggingface.co/Chickaboo/
• Original model: https://huggingface.co/Chickaboo/ChickaQ-V2-Large-Beta/

Original model description:

base_model: - vilm/Quyen-mini-v0.1 - Qwen/Qwen1.5-1.8B-Chat library_name: transformers tags: - mergekit - merge license: mit

Models in the ChickaQ family

• ChickaQ (0.5B)

• ChickaQ-Large (1.8B)

• ChickaQ-V2-Beta (0.9B)

• ChickaQ-V2-Large-Beta (3B)

mergedmodel

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• vilm/Quyen-mini-v0.1
• Qwen/Qwen1.5-1.8B-Chat

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: Qwen/Qwen1.5-1.8B-Chat
      layer_range: [0, 24]
  - sources:
    - model: vilm/Quyen-mini-v0.1
      layer_range: [0, 24]
merge_method: passthrough
dtype: bfloat16

License

---

license: mit license_link: mit