YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

arco-exp-07 - GGUF

Model creator: https://huggingface.co/appvoid/
Original model: https://huggingface.co/appvoid/arco-exp-07/

Name	Quant method	Size
arco-exp-07.Q2_K.gguf	Q2_K	0.2GB
arco-exp-07.IQ3_XS.gguf	IQ3_XS	0.22GB
arco-exp-07.IQ3_S.gguf	IQ3_S	0.22GB
arco-exp-07.Q3_K_S.gguf	Q3_K_S	0.22GB
arco-exp-07.IQ3_M.gguf	IQ3_M	0.23GB
arco-exp-07.Q3_K.gguf	Q3_K	0.24GB
arco-exp-07.Q3_K_M.gguf	Q3_K_M	0.24GB
arco-exp-07.Q3_K_L.gguf	Q3_K_L	0.26GB
arco-exp-07.IQ4_XS.gguf	IQ4_XS	0.27GB
arco-exp-07.Q4_0.gguf	Q4_0	0.28GB
arco-exp-07.IQ4_NL.gguf	IQ4_NL	0.28GB
arco-exp-07.Q4_K_S.gguf	Q4_K_S	0.28GB
arco-exp-07.Q4_K.gguf	Q4_K	0.3GB
arco-exp-07.Q4_K_M.gguf	Q4_K_M	0.3GB
arco-exp-07.Q4_1.gguf	Q4_1	0.31GB
arco-exp-07.Q5_0.gguf	Q5_0	0.34GB
arco-exp-07.Q5_K_S.gguf	Q5_K_S	0.34GB
arco-exp-07.Q5_K.gguf	Q5_K	0.34GB
arco-exp-07.Q5_K_M.gguf	Q5_K_M	0.34GB
arco-exp-07.Q5_1.gguf	Q5_1	0.36GB
arco-exp-07.Q6_K.gguf	Q6_K	0.39GB
arco-exp-07.Q8_0.gguf	Q8_0	0.51GB

Original model description:

base_model:

appvoid/cubby-chat
appvoid/arco-reflection
appvoid/danube-reason-4ep
appvoid/danube-reasoner
appvoid/arco-chat-v0.1 library_name: transformers tags:
mergekit
merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using appvoid/arco-reflection as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: appvoid/danube-reasoner
    parameters:
      density: 0.6
      weight: 0.4
  - model: appvoid/danube-reason-4ep
    parameters:
      density: 0.6
      weight: 0.4
  - model: appvoid/arco-chat-v0.1
    parameters:
      density: 0.6
      weight: 0.3
  - model: appvoid/cubby-chat
    parameters:
      density: 0.6
      weight: 0.4

merge_method: ties
base_model: appvoid/arco-reflection
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Downloads last month: 41

GGUF

Model size

0.5B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for RichardErkhov/appvoid_-_arco-exp-07-gguf

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19