You can deploy this model and start earning money today!

RichardErkhov/
Undi95_-_UtopiaXL-13B-gguf

Name: Undi95_-_UtopiaXL-13B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

UtopiaXL-13B - GGUF

Model creator: https://huggingface.co/Undi95/
Original model: https://huggingface.co/Undi95/UtopiaXL-13B/

Name	Quant method	Size
UtopiaXL-13B.Q2_K.gguf	Q2_K	4.52GB
UtopiaXL-13B.IQ3_XS.gguf	IQ3_XS	4.99GB
UtopiaXL-13B.IQ3_S.gguf	IQ3_S	5.27GB
UtopiaXL-13B.Q3_K_S.gguf	Q3_K_S	5.27GB
UtopiaXL-13B.IQ3_M.gguf	IQ3_M	5.57GB
UtopiaXL-13B.Q3_K.gguf	Q3_K	5.9GB
UtopiaXL-13B.Q3_K_M.gguf	Q3_K_M	5.9GB
UtopiaXL-13B.Q3_K_L.gguf	Q3_K_L	6.45GB
UtopiaXL-13B.IQ4_XS.gguf	IQ4_XS	6.54GB
UtopiaXL-13B.Q4_0.gguf	Q4_0	6.86GB
UtopiaXL-13B.IQ4_NL.gguf	IQ4_NL	6.9GB
UtopiaXL-13B.Q4_K_S.gguf	Q4_K_S	6.91GB
UtopiaXL-13B.Q4_K.gguf	Q4_K	7.33GB
UtopiaXL-13B.Q4_K_M.gguf	Q4_K_M	7.33GB
UtopiaXL-13B.Q4_1.gguf	Q4_1	7.61GB
UtopiaXL-13B.Q5_0.gguf	Q5_0	8.36GB
UtopiaXL-13B.Q5_K_S.gguf	Q5_K_S	8.36GB
UtopiaXL-13B.Q5_K.gguf	Q5_K	8.6GB
UtopiaXL-13B.Q5_K_M.gguf	Q5_K_M	8.6GB
UtopiaXL-13B.Q5_1.gguf	Q5_1	9.1GB
UtopiaXL-13B.Q6_K.gguf	Q6_K	9.95GB
UtopiaXL-13B.Q8_0.gguf	Q8_0	12.88GB

Original model description:

license: cc-by-nc-4.0 tags:

not-for-all-audiences
nsfw

Description

This repo contains fp16 files of UtopiaXL-13B, a merge I have done with the new layer shuffle method from mergekit (thank you Charles for adding my request to your project!)

This is more a proof of concept showing the following:

Llama2 is very flexible
Llama2 don't care about what is finetuned on the layers specifically if you keep them in the same order
Clean merge (no ties, no SLERP, etc...) with only layer is possible without breaking something
Deleting special tokens/using model with special token don't break the model
Alpaca win, always. So use it.

The name "XL" come from the absurd amount of model pushed into it.

Models and loras used

The sauce

!mergekit-layershuffle ./UtopiaXL \
  --model Undi95/Utopia-13B --weight 0.4 \
  --model KoboldAI/LLAMA2-13B-Holodeck-1 --weight 0.1 \
  --model Undi95/PsyMedRP-v1-13B --weight 0.1 \
  --model PygmalionAI/pygmalion-2-13b --weight 0.25 \
  --model Heralax/Cat-0.5 --weight 0.1 \
  --model KoboldAI/LLaMA2-13B-TiefighterLR --weight 0.1 \
  --model Heralax/Augmental-13b-two-epochs --weight 0.1 \
  --write-yaml UtopiaXL.yaml

=========================

merge_method: passthrough
slices:
- sources:
  - layer_range:
    - 0
    - 1
    model: KoboldAI/LLAMA2-13B-Holodeck-1
- sources:
  - layer_range:
    - 1
    - 4
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 4
    - 5
    model: PygmalionAI/pygmalion-2-13b
- sources:
  - layer_range:
    - 5
    - 6
    model: Undi95/PsyMedRP-v1-13B
- sources:
  - layer_range:
    - 6
    - 7
    model: KoboldAI/LLaMA2-13B-TiefighterLR
- sources:
  - layer_range:
    - 7
    - 8
    model: PygmalionAI/pygmalion-2-13b
- sources:
  - layer_range:
    - 8
    - 9
    model: Undi95/PsyMedRP-v1-13B
- sources:
  - layer_range:
    - 9
    - 10
    model: PygmalionAI/pygmalion-2-13b
- sources:
  - layer_range:
    - 10
    - 13
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 13
    - 14
    model: Heralax/Cat-0.5
- sources:
  - layer_range:
    - 14
    - 17
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 17
    - 18
    model: Heralax/Augmental-13b-two-epochs
- sources:
  - layer_range:
    - 18
    - 19
    model: KoboldAI/LLaMA2-13B-TiefighterLR
- sources:
  - layer_range:
    - 19
    - 22
    model: PygmalionAI/pygmalion-2-13b
- sources:
  - layer_range:
    - 22
    - 23
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 23
    - 25
    model: PygmalionAI/pygmalion-2-13b
- sources:
  - layer_range:
    - 25
    - 27
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 27
    - 28
    model: Heralax/Cat-0.5
- sources:
  - layer_range:
    - 28
    - 30
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 30
    - 31
    model: Heralax/Augmental-13b-two-epochs
- sources:
  - layer_range:
    - 31
    - 32
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 32
    - 33
    model: Heralax/Cat-0.5
- sources:
  - layer_range:
    - 33
    - 34
    model: Heralax/Augmental-13b-two-epochs
- sources:
  - layer_range:
    - 34
    - 35
    model: Undi95/PsyMedRP-v1-13B
- sources:
  - layer_range:
    - 35
    - 36
    model: Heralax/Augmental-13b-two-epochs
- sources:
  - layer_range:
    - 36
    - 37
    model: Undi95/Utopia-13B
- sources:
  - layer_range:
    - 37
    - 38
    model: KoboldAI/LLAMA2-13B-Holodeck-1
- sources:
  - layer_range:
    - 38
    - 39
    model: PygmalionAI/pygmalion-2-13b
- sources:
  - layer_range:
    - 39
    - 40
    model: KoboldAI/LLAMA2-13B-Holodeck-1

=========================

=> Applying Undi95/Storytelling-v2.1-13B-lora x 0.1
=> Trained on LimaRP for +2h
=> Applying Undi95/LimaRP-UtopiaXL-13B-v3-lora x 0.35

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

A big thanks to Charles for adding the layer shuffle method to his tool mergekit and Henky/KoboldAI for the machine he let me use.

If you want to support me, you can here.

RichardErkhov/Undi95_-_UtopiaXL-13B-gguf