You can deploy this model and start earning money today!

RichardErkhov/
NeverSleep_-_Mistral-11B-AirOmniMix-gguf

Name: NeverSleep_-_Mistral-11B-AirOmniMix-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-11B-AirOmniMix - GGUF

Model creator: https://huggingface.co/NeverSleep/
Original model: https://huggingface.co/NeverSleep/Mistral-11B-AirOmniMix/

Name	Quant method	Size
Mistral-11B-AirOmniMix.Q2_K.gguf	Q2_K	3.73GB
Mistral-11B-AirOmniMix.IQ3_XS.gguf	IQ3_XS	4.14GB
Mistral-11B-AirOmniMix.IQ3_S.gguf	IQ3_S	4.37GB
Mistral-11B-AirOmniMix.Q3_K_S.gguf	Q3_K_S	4.34GB
Mistral-11B-AirOmniMix.IQ3_M.gguf	IQ3_M	4.51GB
Mistral-11B-AirOmniMix.Q3_K.gguf	Q3_K	4.84GB
Mistral-11B-AirOmniMix.Q3_K_M.gguf	Q3_K_M	4.84GB
Mistral-11B-AirOmniMix.Q3_K_L.gguf	Q3_K_L	5.26GB
Mistral-11B-AirOmniMix.IQ4_XS.gguf	IQ4_XS	5.43GB
Mistral-11B-AirOmniMix.Q4_0.gguf	Q4_0	5.66GB
Mistral-11B-AirOmniMix.IQ4_NL.gguf	IQ4_NL	5.72GB
Mistral-11B-AirOmniMix.Q4_K_S.gguf	Q4_K_S	5.7GB
Mistral-11B-AirOmniMix.Q4_K.gguf	Q4_K	6.02GB
Mistral-11B-AirOmniMix.Q4_K_M.gguf	Q4_K_M	6.02GB
Mistral-11B-AirOmniMix.Q4_1.gguf	Q4_1	6.27GB
Mistral-11B-AirOmniMix.Q5_0.gguf	Q5_0	6.89GB
Mistral-11B-AirOmniMix.Q5_K_S.gguf	Q5_K_S	6.89GB
Mistral-11B-AirOmniMix.Q5_K.gguf	Q5_K	7.08GB
Mistral-11B-AirOmniMix.Q5_K_M.gguf	Q5_K_M	7.08GB
Mistral-11B-AirOmniMix.Q5_1.gguf	Q5_1	7.51GB
Mistral-11B-AirOmniMix.Q6_K.gguf	Q6_K	8.2GB
Mistral-11B-AirOmniMix.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: cc-by-nc-4.0

Replaced Zephyr by Airoboros 2.2 in the mix.

Description

This repo contains fp16 files of Mistral-11B-AirOmniMix.

Model used

Prompt template

The best one after further testing is this one, since Zephyr is out of the merge:

USER: <prompt>
ASSISTANT:

But this one work too:

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

### Instruction:
{prompt}

### Response:

Or use any prompting system from one of the 4 source model, should work.

The secret sauce

Mistral-11B-OpenOrcaPlatypus :

slices:
  - sources:
    - model: Open-Orca/Mistral-7B-OpenOrca
      layer_range: [0, 24]
  - sources:
    - model: akjindal53244/Mistral-7B-v0.1-Open-Platypus
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

Mistral-11B-CC-Airo :

slices:
  - sources:
    - model: "/content/drive/MyDrive/CC-v1.1-7B-bf16"
      layer_range: [0, 24]
  - sources:
    - model: "/content/drive/MyDrive/Mistral-7B-Airoboros-2.2-bf16"
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

Mistral-11B-AirOmniMix :

slices:
  - sources:
      - model: Mistral-11B-OpenOrcaPlatypus
        layer_range: [0, 48]
      - model: Mistral-11B-CC-Airo
        layer_range: [0, 48]
merge_method: slerp
base_model: Mistral-11B-OpenOrcaPlatypus
parameters:
  t:
    - filter: lm_head 
      value: [0.75]
    - filter: embed_tokens
      value: [0.75]
    - filter: self_attn
      value: [0.75, 0.25]
    - filter: mlp
      value:  [0.25, 0.75]
    - filter: layernorm
      value: [0.5, 0.5]
    - filter: modelnorm
      value: [0.75]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

I use mergekit for all the manipulation told here.

Some scoring I done myself

hf-causal-experimental (pretrained=/content/drive/MyDrive/Mistral-11B-AirOmniMix), limit: None, provide_description: False, num_fewshot: 0, batch_size: 4

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	0.5452	±	0.0146
		acc_norm	0.5836	±	0.0144
arc_easy	0	acc	0.8321	±	0.0077
		acc_norm	0.8119	±	0.0080
hellaswag	0	acc	0.6381	±	0.0048
		acc_norm	0.8250	±	0.0038
piqa	0	acc	0.8096	±	0.0092
		acc_norm	0.8243	±	0.0089
truthfulqa_mc	1	mc1	0.3941	±	0.0171
		mc2	0.5606	±	0.0155
winogrande	0	acc	0.7395	±	0.0123

Others

Special thanks to Sushi, Henky for the machine he give me for big task, and Charles Goddard for his amazing tool.

If you want to support me, you can here.

RichardErkhov/NeverSleep_-_Mistral-11B-AirOmniMix-gguf