Hippius
mainsafetensorsbf16Publictransformersbase: []

long-killer/teutonic-q3-4b-5ehzn9kc-t026

sha256:3daeaa6b477af839a256bcf59b1c080dd354e9b3a94cd0f603fe58f10796c58f·Indexed 1h ago

Parameters

4.4B

Total size

8.2 GB

Files

8

Quantization

BF16

README.md

1.0 KB

merged-hier-pairs-t026

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

  • /teamspace/studios/this_studio/merged-pair-25-22-t035
  • /teamspace/studios/this_studio/merged-slerp-t035

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: /teamspace/studios/this_studio/merged-slerp-t035
        layer_range: [0, 36]
      - model: /teamspace/studios/this_studio/merged-pair-25-22-t035
        layer_range: [0, 36]

merge_method: slerp
base_model: /teamspace/studios/this_studio/merged-slerp-t035

parameters:
  t: 0.26

dtype: bfloat16

tokenizer:
  source: /teamspace/studios/this_studio/merged-slerp-t035

chat_template: auto

Model architecture

config.json
Architecture
Qwen3ForCausalLM
Model type
qwen3
Hidden size
2,560
Layers
36
Attention heads
32 (8 kv)
FFN size
9,728
Vocab size
151,669
Context window
40K

Files

8 items
  • model-00001-of-00002.safetensors

    24725b08406b

    4.6 GB

    safetensors

  • model-00002-of-00002.safetensors

    99052824591a

    3.6 GB

    safetensors

  • tokenizer.json

    be75606093db

    10.9 MB

  • model.safetensors.index.json

    4ab274b1bcbe

    32.1 KB

  • config.json

    a097ba87138a

    1.6 KB

  • README.md

    2ec4cd923b6a

    1.0 KB

  • tokenizer_config.json

    2e3bd3cb5055

    693 B

  • mergekit_config.yml

    08a1563a1a58

    426 B