kromeurus's picture
Update README.md
c76cd6c verified
|
raw
history blame
2.91 kB
metadata
base_model:
  - ArliAI/ArliAI-Llama-3-8B-Formax-v1.0
  - gradientai/Llama-3-8B-Instruct-Gradient-1048k
  - ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.0
  - Sao10K/L3.1-8B-Niitama-v1.1
  - Sao10K/L3-8B-Stheno-v3.3-32K
  - tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
  - Sao10K/L3-8B-Tamamo-v1
  - Edgerunners/Lyraea-large-llama-3.1
library_name: transformers
tags:
  - mergekit
  - merge

HUZZAH, a model that's actually good! Just took seven tries. Fixed spacial understanding and literacy, toned down a little of the clingy instruct following, and more turn based RP forward.

Quants

A few GGUFs by me.

Details & Recommended Settings

(Still testing; details subject to change)

Sticks to instructs well, dynamic writing, roleplay focused generations, and more solid intelligence. Less rambley though still outputs a bit of text. Has near perfect recall up to 32K. Be clear and explicit with model instructs, including the intended format (Asterix, quotes, etc).

Rec. Settings:

Template: L3
Temperature: 1.3
Min P: 0.1
Repeat Penalty: 1.05
Repeat Penalty Tokens: 256
Dyn Temp: 0.9-1.05 at 0.1
Smooth Sampl: 0.18

Merge Theory

This sucked. Repalce RP Hermes back with Edgerunners Lyraea and swapped Niitama with L3.1 Niitama.

Config

slices:
- sources:
  - layer_range: [0, 16]
    model: ArliAI/ArliAI-Llama-3-8B-Formax-v1.0
- sources:
  - layer_range: [16, 32]
    model: gradientai/Llama-3-8B-Instruct-Gradient-1048k
parameters:
  int8_mask: true
merge_method: passthrough
dtype: float32
out_dtype: bfloat16
name: formax.ext
---
models: 
  - model: formax.ext
    parameters:
      weight: 1.1
base_model: ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.0
parameters:
  normalize: false
  int8_mask: true
merge_method: dare_linear
dtype: float32
out_dtype: bfloat16
tokenizer_source: base
name: formaxext.3.1
---
models: 
  - model: Sao10K/L3-8B-Niitama-v1
    parameters:
      weight: 0.5
  - model: Sao10K/L3-8B-Stheno-v3.3-32K
    parameters:
      weight: 0.6
base_model: tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
parameters:
  normalize: false
  int8_mask: true
merge_method: dare_linear
dtype: float32
out_dtype: bfloat16
tokenizer_source: base
name: siith.3.1
---
models:
    - model: siith.3.1
    - model: Sao10K/L3-8B-Tamamo-v1
base_model: Edgerunners/Lyraea-large-llama-3.1
parameters:
  normalize: false
  int8_mask: true
merge_method: model_stock
dtype: float32
out_dtype: bfloat16
name: siithamol3.1
---
models: 
  - model: siithamol3.1
    parameters:
      weight: [0.5, 0,8, 0.8, 0.9, 1]
      density: 0.9
      gamma: 0.01
  - model: formaxext.3.1
    parameters:
      weight: [0.5, 0.2, 0.2, 0.1, 0]
      density: 0.9
      gamma: 0.01
base_model: siithamol3.1
parameters:
  normalize: false
  int8_mask: true
merge_method: breadcrumbs_ties
dtype: float32
out_dtype: bfloat16
name: siithamov3