RichardErkhov/Undi95_-_Toppy-M-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Toppy-M-7B - GGUF

• Model creator: https://huggingface.co/Undi95/
• Original model: https://huggingface.co/Undi95/Toppy-M-7B/

Name	Quant method	Size
Toppy-M-7B.Q2_K.gguf	Q2_K	2.53GB
Toppy-M-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Toppy-M-7B.IQ3_S.gguf	IQ3_S	2.96GB
Toppy-M-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Toppy-M-7B.IQ3_M.gguf	IQ3_M	3.06GB
Toppy-M-7B.Q3_K.gguf	Q3_K	3.28GB
Toppy-M-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Toppy-M-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Toppy-M-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Toppy-M-7B.Q4_0.gguf	Q4_0	3.83GB
Toppy-M-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Toppy-M-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Toppy-M-7B.Q4_K.gguf	Q4_K	4.07GB
Toppy-M-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Toppy-M-7B.Q4_1.gguf	Q4_1	4.24GB
Toppy-M-7B.Q5_0.gguf	Q5_0	4.65GB
Toppy-M-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Toppy-M-7B.Q5_K.gguf	Q5_K	4.78GB
Toppy-M-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Toppy-M-7B.Q5_1.gguf	Q5_1	5.07GB
Toppy-M-7B.Q6_K.gguf	Q6_K	5.53GB
Toppy-M-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-4.0 tags: - not-for-all-audiences - nsfw

Description

This repo contains fp16 files of Toppy-M-7B, a merge I have done with the new task_arithmetic merge method from mergekit.

This project was a request from BlueNipples : link

Models and loras used

• openchat/openchat_3.5
• NousResearch/Nous-Capybara-7B-V1.9
• HuggingFaceH4/zephyr-7b-beta
• lemonilia/AshhLimaRP-Mistral-7B
• Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b
• Undi95/Mistral-pippa-sharegpt-7b-qlora

The sauce

openchat/openchat_3.5
lemonilia/AshhLimaRP-Mistral-7B (LoRA) x 0.38

NousResearch/Nous-Capybara-7B-V1.9
Vulkane/120-Days-of-Sodom-LoRA-Mistral-7b x 0.27

HuggingFaceH4/zephyr-7b-beta
Undi95/Mistral-pippa-sharegpt-7b-qlora x 0.38

merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: mistralai/Mistral-7B-v0.1
  - model: Undi95/zephyr-7b-beta-pippa-sharegpt
    parameters:
      weight: 0.42
  - model: Undi95/Nous-Capybara-7B-V1.9-120-Days
    parameters:
      weight: 0.29
  - model: Undi95/openchat_3.5-LimaRP-13B
    parameters:
      weight: 0.48
dtype: bfloat16

Prompt template: Alpaca

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

### Instruction:
{prompt}

### Response:

If you want to support me, you can here.