You can deploy this model and start earning money today!

RichardErkhov/
appvoid_-_exp-xl-2-gguf

Name: appvoid_-_exp-xl-2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

exp-xl-2 - GGUF

Model creator: https://huggingface.co/appvoid/
Original model: https://huggingface.co/appvoid/exp-xl-2/

Name	Quant method	Size
exp-xl-2.Q2_K.gguf	Q2_K	0.66GB
exp-xl-2.IQ3_XS.gguf	IQ3_XS	0.74GB
exp-xl-2.IQ3_S.gguf	IQ3_S	0.77GB
exp-xl-2.Q3_K_S.gguf	Q3_K_S	0.76GB
exp-xl-2.IQ3_M.gguf	IQ3_M	0.79GB
exp-xl-2.Q3_K.gguf	Q3_K	0.84GB
exp-xl-2.Q3_K_M.gguf	Q3_K_M	0.84GB
exp-xl-2.Q3_K_L.gguf	Q3_K_L	0.9GB
exp-xl-2.IQ4_XS.gguf	IQ4_XS	0.93GB
exp-xl-2.Q4_0.gguf	Q4_0	0.97GB
exp-xl-2.IQ4_NL.gguf	IQ4_NL	0.98GB
exp-xl-2.Q4_K_S.gguf	Q4_K_S	0.98GB
exp-xl-2.Q4_K.gguf	Q4_K	1.02GB
exp-xl-2.Q4_K_M.gguf	Q4_K_M	1.02GB
exp-xl-2.Q4_1.gguf	Q4_1	1.07GB
exp-xl-2.Q5_0.gguf	Q5_0	1.16GB
exp-xl-2.Q5_K_S.gguf	Q5_K_S	1.16GB
exp-xl-2.Q5_K.gguf	Q5_K	1.19GB
exp-xl-2.Q5_K_M.gguf	Q5_K_M	1.19GB
exp-xl-2.Q5_1.gguf	Q5_1	1.26GB
exp-xl-2.Q6_K.gguf	Q6_K	1.37GB
exp-xl-2.Q8_0.gguf	Q8_0	1.78GB

Original model description:

base_model:

h2oai/h2o-danube3-4b-chat 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 passthrough merge method.

Models Merged

The following models were included in the merge:

h2oai/h2o-danube3-4b-chat

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
    - model: h2oai/h2o-danube3-4b-chat
      layer_range: [0, 6]
  - sources:
    - model: h2oai/h2o-danube3-4b-chat
      layer_range: [20, 24]
merge_method: passthrough
dtype: float16

RichardErkhov/appvoid_-_exp-xl-2-gguf