final_model

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:

Configuration

The following YAML configuration was used to produce this model:

base_model: RoyJoy/llama-jan16
dtype: bfloat16
merge_method: slerp
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.12347326361005005
  sources:
  - layer_range: [0, 2]
    model: RoyJoy/llama-jan16
  - layer_range: [0, 2]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.4274371274240911
  sources:
  - layer_range: [2, 4]
    model: luaqi/llama_01141
  - layer_range: [2, 4]
    model: RoyJoy/llama-jan16
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.45996115782476704
  sources:
  - layer_range: [4, 6]
    model: RoyJoy/llama-jan16
  - layer_range: [4, 6]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.4472011798824502
  sources:
  - layer_range: [6, 8]
    model: luaqi/llama_01141
  - layer_range: [6, 8]
    model: RoyJoy/llama-jan16
- base_model: luaqi/llama_01141
  parameters:
    t: 0.3626764469890088
  sources:
  - layer_range: [8, 10]
    model: luaqi/llama_01141
  - layer_range: [8, 10]
    model: RoyJoy/llama-jan16
- base_model: luaqi/llama_01141
  parameters:
    t: 0.3047811008444177
  sources:
  - layer_range: [10, 12]
    model: luaqi/llama_01141
  - layer_range: [10, 12]
    model: RoyJoy/llama-jan16
- base_model: luaqi/llama_01141
  parameters:
    t: 0.4191841705224738
  sources:
  - layer_range: [12, 14]
    model: luaqi/llama_01141
  - layer_range: [12, 14]
    model: RoyJoy/llama-jan16
- base_model: luaqi/llama_01141
  parameters:
    t: 0.48611727995422105
  sources:
  - layer_range: [14, 16]
    model: luaqi/llama_01141
  - layer_range: [14, 16]
    model: RoyJoy/llama-jan16
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.49327335687995005
  sources:
  - layer_range: [16, 18]
    model: RoyJoy/llama-jan16
  - layer_range: [16, 18]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.45941960258651676
  sources:
  - layer_range: [18, 20]
    model: luaqi/llama_01141
  - layer_range: [18, 20]
    model: RoyJoy/llama-jan16
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.4951314948007201
  sources:
  - layer_range: [20, 22]
    model: RoyJoy/llama-jan16
  - layer_range: [20, 22]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.40612891630067377
  sources:
  - layer_range: [22, 24]
    model: luaqi/llama_01141
  - layer_range: [22, 24]
    model: RoyJoy/llama-jan16
- base_model: luaqi/llama_01141
  parameters:
    t: 0.4717773146173076
  sources:
  - layer_range: [24, 26]
    model: luaqi/llama_01141
  - layer_range: [24, 26]
    model: RoyJoy/llama-jan16
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.35856355412368607
  sources:
  - layer_range: [26, 28]
    model: RoyJoy/llama-jan16
  - layer_range: [26, 28]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.474645297482983
  sources:
  - layer_range: [28, 30]
    model: luaqi/llama_01141
  - layer_range: [28, 30]
    model: RoyJoy/llama-jan16
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.4113346104507393
  sources:
  - layer_range: [30, 32]
    model: RoyJoy/llama-jan16
  - layer_range: [30, 32]
    model: luaqi/llama_01141
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.42271098156195525
  sources:
  - layer_range: [32, 34]
    model: RoyJoy/llama-jan16
  - layer_range: [32, 34]
    model: luaqi/llama_01141
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.43002043563359715
  sources:
  - layer_range: [34, 36]
    model: RoyJoy/llama-jan16
  - layer_range: [34, 36]
    model: luaqi/llama_01141
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.4024317979779294
  sources:
  - layer_range: [36, 38]
    model: RoyJoy/llama-jan16
  - layer_range: [36, 38]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.42781244776074845
  sources:
  - layer_range: [38, 40]
    model: luaqi/llama_01141
  - layer_range: [38, 40]
    model: RoyJoy/llama-jan16
- base_model: luaqi/llama_01141
  parameters:
    t: 0.4744212098311982
  sources:
  - layer_range: [40, 42]
    model: luaqi/llama_01141
  - layer_range: [40, 42]
    model: RoyJoy/llama-jan16
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.42107835961309203
  sources:
  - layer_range: [42, 44]
    model: RoyJoy/llama-jan16
  - layer_range: [42, 44]
    model: luaqi/llama_01141
- base_model: RoyJoy/llama-jan16
  parameters:
    t: 0.3570606753644864
  sources:
  - layer_range: [44, 46]
    model: RoyJoy/llama-jan16
  - layer_range: [44, 46]
    model: luaqi/llama_01141
- base_model: luaqi/llama_01141
  parameters:
    t: 0.49464856531161844
  sources:
  - layer_range: [46, 48]
    model: luaqi/llama_01141
  - layer_range: [46, 48]
    model: RoyJoy/llama-jan16
Downloads last month
3
Safetensors
Model size
13.9B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for deepcoreCoalbiter/slerped_freddy

Merge model
this model