mergekit-community_-_Mathing-1.5B-gguf

RichardErkhov/mergekit-community_-_Mathing-1.5B-gguf

mergekit-community_-_Mathing-1.5B-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

294

15% of all-time downloads

All-time downloads

Public

Repo size

19 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf22 GB · 100%

At a glance

Access: Public
Created: Aug 25, 2024
Updated: Aug 25, 2024
SHA: 78a6fdda

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mathing-1.5B - GGUF

Model creator: https://huggingface.co/mergekit-community/
Original model: https://huggingface.co/mergekit-community/Mathing-1.5B/

Name	Quant method	Size
Mathing-1.5B.Q2_K.gguf	Q2_K	0.64GB
Mathing-1.5B.IQ3_XS.gguf	IQ3_XS	0.7GB
Mathing-1.5B.IQ3_S.gguf	IQ3_S	0.73GB
Mathing-1.5B.Q3_K_S.gguf	Q3_K_S	0.73GB
Mathing-1.5B.IQ3_M.gguf	IQ3_M	0.74GB
Mathing-1.5B.Q3_K.gguf	Q3_K	0.78GB
Mathing-1.5B.Q3_K_M.gguf	Q3_K_M	0.78GB
Mathing-1.5B.Q3_K_L.gguf	Q3_K_L	0.82GB
Mathing-1.5B.IQ4_XS.gguf	IQ4_XS	0.86GB
Mathing-1.5B.Q4_0.gguf	Q4_0	0.89GB
Mathing-1.5B.IQ4_NL.gguf	IQ4_NL	0.9GB
Mathing-1.5B.Q4_K_S.gguf	Q4_K_S	0.9GB
Mathing-1.5B.Q4_K.gguf	Q4_K	0.94GB
Mathing-1.5B.Q4_K_M.gguf	Q4_K_M	0.94GB
Mathing-1.5B.Q4_1.gguf	Q4_1	0.97GB
Mathing-1.5B.Q5_0.gguf	Q5_0	1.05GB
Mathing-1.5B.Q5_K_S.gguf	Q5_K_S	1.05GB
Mathing-1.5B.Q5_K.gguf	Q5_K	1.07GB
Mathing-1.5B.Q5_K_M.gguf	Q5_K_M	1.07GB
Mathing-1.5B.Q5_1.gguf	Q5_1	1.13GB
Mathing-1.5B.Q6_K.gguf	Q6_K	1.22GB
Mathing-1.5B.Q8_0.gguf	Q8_0	1.58GB

Original model description:

base_model:

Qwen/Qwen2-Math-1.5B-Instruct
arcee-ai/arcee-lite 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 SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: Qwen/Qwen2-Math-1.5B-Instruct
    layer_range:
    - 0
    - 24
  - model: arcee-ai/arcee-lite
    layer_range:
    - 0
    - 24
merge_method: slerp
base_model: arcee-ai/arcee-lite
parameters:
  t:
  - filter: self_attn
    value:
    - 0
    - 0.55
    - 0.3
    - 0.65
    - 1
  - filter: mlp
    value:
    - 1
    - 0.55
    - 0.7
    - 0.65
    - 0
  - value: 0.448
dtype: bfloat16

Created: Aug 25, 2024
Updated: Aug 25, 2024