Replete-AI_-_Phi-5B-Test-gguf

RichardErkhov/Replete-AI_-_Phi-5B-Test-gguf

Replete-AI_-_Phi-5B-Test-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

1% of all-time downloads

All-time downloads

4.4K

Public

Repo size

60.9 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf70.7 GB · 100%

At a glance

Access: Public
Created: Oct 3, 2024
Updated: Oct 4, 2024
SHA: 23746a1c

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-5B-Test - GGUF

Model creator: https://huggingface.co/Replete-AI/
Original model: https://huggingface.co/Replete-AI/Phi-5B-Test/

Name	Quant method	Size
Phi-5B-Test.Q2_K.gguf	Q2_K	1.92GB
Phi-5B-Test.IQ3_XS.gguf	IQ3_XS	2.08GB
Phi-5B-Test.IQ3_S.gguf	IQ3_S	2.18GB
Phi-5B-Test.Q3_K_S.gguf	Q3_K_S	2.18GB
Phi-5B-Test.IQ3_M.gguf	IQ3_M	2.31GB
Phi-5B-Test.Q3_K.gguf	Q3_K	2.5GB
Phi-5B-Test.Q3_K_M.gguf	Q3_K_M	2.5GB
Phi-5B-Test.Q3_K_L.gguf	Q3_K_L	2.78GB
Phi-5B-Test.IQ4_XS.gguf	IQ4_XS	2.69GB
Phi-5B-Test.Q4_0.gguf	Q4_0	2.81GB
Phi-5B-Test.IQ4_NL.gguf	IQ4_NL	2.84GB
Phi-5B-Test.Q4_K_S.gguf	Q4_K_S	2.84GB
Phi-5B-Test.Q4_K.gguf	Q4_K	3.07GB
Phi-5B-Test.Q4_K_M.gguf	Q4_K_M	3.07GB
Phi-5B-Test.Q4_1.gguf	Q4_1	3.11GB
Phi-5B-Test.Q5_0.gguf	Q5_0	3.42GB
Phi-5B-Test.Q5_K_S.gguf	Q5_K_S	3.42GB
Phi-5B-Test.Q5_K.gguf	Q5_K	3.55GB
Phi-5B-Test.Q5_K_M.gguf	Q5_K_M	3.55GB
Phi-5B-Test.Q5_1.gguf	Q5_1	3.72GB
Phi-5B-Test.Q6_K.gguf	Q6_K	4.05GB
Phi-5B-Test.Q8_0.gguf	Q8_0	5.25GB

Original model description:

base_model: [] tags:

mergekit
merge license: mit

Untitled Model (1)

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:

https://huggingface.co/liminerity/Phigments12
https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml
and then depth upscaled

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: liminerity/Phigments12
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: l3utterfly/phi-2-layla-v1-chatml
    parameters:
      density: 0.8
      weight: [0, 0.5, 0.7, 1] # weight gradient
 
merge_method: dare_ties
base_model: liminerity/Phigments12
parameters:
  normalize: true
  int8_mask: true
dtype: float16

dtype: float16
merge_method: passthrough
slices:
  - sources:
    - model: phi/
      layer_range: [0,32]
  - sources:
    - model: phi/
      layer_range: [0,32]

Join the Replete AI Discord here!

Created: Oct 3, 2024
Updated: Oct 4, 2024