NOTES: Looks promising...In testing...*
###################################################################################
merge
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:
Configuration
The following YAML configuration was used to produce this model:
#--DUAL MODEL MERGE SETUP---
# TRY AGAIN, BUT COPY OVER THE CORRECT .JSON FILES FROM
# HARMONIC HARLEQUIN SO IT CAN GGUF.. maybe..
# The models we are going to use.
const_tag: &BASE_MODEL Undi95/PsyMedRP-v1-20B
const_tag: &MODEL1 Elfrino/XwinXtended-20B # Will this guy cause me headaches?
const_tag: &MODEL2 Undi95/PsyMedRP-v1-20B
# The amount to scale the contribution to the residual stream (to hopefully reduce overshoot).
const_tag: &RESIDUAL_SCALE_FACTOR 0.71 # back to 0.7
model1-filter-env: &MODEL1_FILTER_ENV
parameters:
scale:
- filter: down_proj
value: *RESIDUAL_SCALE_FACTOR
- value: 1.0
model2-filter-env: &MODEL2_FILTER_ENV
parameters:
scale:
- filter: down_proj
value: *RESIDUAL_SCALE_FACTOR
- value: 1.0
slices:
# The first 10 layers are not duplicated.
- sources:
- model: *BASE_MODEL
layer_range: [0, 10]
- sources:
- model: *MODEL1
layer_range: [10, 11]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [10, 11]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [11, 12]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [11, 12]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [12, 13]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [12, 13]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [13, 14]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [13, 14]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [14, 15]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [14, 15]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [15, 16]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [15, 16]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [16, 17]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [16, 17]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [17, 18]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [17, 18]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [18, 19]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [18, 19]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [19, 20]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [19, 20]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [20, 21]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [20, 21]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [21, 22]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [21, 22]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [22, 23]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [22, 23]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [23, 24]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [23, 24]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [24, 25]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [24, 25]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [25, 26]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [25, 26]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [26, 27]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [26, 27]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [27, 28]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [27, 28]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [28, 29]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [28, 29]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [29, 30]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [29, 30]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [30, 31]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [30, 31]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [31, 32]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [31, 32]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [32, 33]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [32, 33]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [33, 34]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [33, 34]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [34, 35]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [34, 35]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [35, 36]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [35, 36]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [36, 37]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [36, 37]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [37, 38]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [37, 38]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [38, 39]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [38, 39]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [39, 40]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [39, 40]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [40, 41]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [40, 41]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [41, 42]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [41, 42]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [42, 43]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [42, 43]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [43, 44]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [43, 44]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [44, 45]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [44, 45]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [45, 46]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [45, 46]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [46, 47]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [46, 47]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [47, 48]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [47, 48]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [48, 49]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [48, 49]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [49, 50]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [49, 50]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [50, 51]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [50, 51]
<<: *MODEL2_FILTER_ENV
- sources:
- model: *MODEL1
layer_range: [51, 52]
<<: *MODEL1_FILTER_ENV
- sources:
- model: *MODEL2
layer_range: [51, 52]
<<: *MODEL2_FILTER_ENV
# The last 10 layers are not duplicated.
- sources:
- model: *BASE_MODEL
layer_range: [52, 62]
merge_method: passthrough
dtype: bfloat16
- Downloads last month
- 8
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.