Nymeria

  • Upgraded SimPO.
  • A touch of 3SOME, Lumimaid and Jamet Blackroot resulting a slightly different prose and wider RP vocab.
  • Leans slightly more on nsfw than the original.

SillyTavern

Text Completion presets

temp 0.9
top_k 30
top_p 0.75
min_p 0.2
rep_pen 1.1
smooth_factor 0.25
smooth_curve 1

Advanced Formatting

Context & Instruct preset by Virt-io

Instruct Mode: Enabled

merge

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

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:


slices:
  - sources:
      - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
        layer_range: [0, 32]
      - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
        layer_range: [0, 32]
merge_method: slerp
base_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0.7, 0.3, 0.3, 0.3]
    - filter: mlp
      value: [0.3, 0.7, 0.7, 0.7]
    - value: 0.4
dtype: bfloat16

L3-Lumimaid-Jamet-Blackroot-8B


slices:
  - sources:
      - model: tannedbum/L3-Lumimaid-Jamet-Blackroot-8B
        layer_range: [0, 32]
      - model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO
        layer_range: [0, 32]
merge_method: slerp
base_model: tannedbum/L3-Lumimaid-Jamet-Blackroot-8B
parameters:
  t:
    - filter: self_attn
      value: [0.3, 0.7, 0.7, 0.7]
    - filter: mlp
      value: [0.7, 0.3, 0.3, 0.3]
    - value: 0.6
dtype: bfloat16

L3-SimPO-Lumimaid-Jamet-Blackroot-8B


slices:
  - sources:
      - model: Sao10K/L3-8B-Stheno-v3.2
        layer_range: [0, 32]
      - model: TheDrummer/Llama-3SOME-8B-v2
        layer_range: [0, 32]
merge_method: slerp
base_model: Sao10K/L3-8B-Stheno-v3.2
parameters:
  t:
    - filter: self_attn
      value: [0.3, 0.3, 0.7, 0.3]
    - filter: mlp
      value: [0.7, 0.7, 0.3, 0.7]
    - value: 0.4
dtype: bfloat16

L3-Stheno-3SOME-8B


slices:
  - sources:
      - model: tannedbum/L3-Stheno-3SOME-8B
        layer_range: [0, 32]
      - model: tannedbum/L3-SimPO-Lumimaid-Jamet-Blackroot-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: tannedbum/L3-Stheno-3SOME-8B
parameters:
  t:
    - filter: self_attn
      value: [0.4, 0.3, 0.3, 0.6]
    - filter: mlp
      value: [0.6, 0.7, 0.7, 0.4]
    - value: 0.4
dtype: bfloat16

L3-Nymeria-v2-8B


Want to support my work ? My Ko-fi page: https://ko-fi.com/tannedbum

Downloads last month
1,466
Safetensors
Model size
8.03B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for tannedbum/L3-Nymeria-v2-8B

Spaces using tannedbum/L3-Nymeria-v2-8B 6