Frowning_-_L3-Stheno-v3.2-15B-gguf

RichardErkhov/Frowning_-_L3-Stheno-v3.2-15B-gguf

Frowning_-_L3-Stheno-v3.2-15B-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

7% of all-time downloads

All-time downloads

1.1K

Public

Repo size

172 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf199 GB · 100%

At a glance

Access: Public
Created: Oct 6, 2024
Updated: Oct 7, 2024
SHA: 124d0fdb

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3-Stheno-v3.2-15B - GGUF

Model creator: https://huggingface.co/Frowning/
Original model: https://huggingface.co/Frowning/L3-Stheno-v3.2-15B/

Name	Quant method	Size
L3-Stheno-v3.2-15B.Q2_K.gguf	Q2_K	5.35GB
L3-Stheno-v3.2-15B.IQ3_XS.gguf	IQ3_XS	5.94GB
L3-Stheno-v3.2-15B.IQ3_S.gguf	IQ3_S	6.24GB
L3-Stheno-v3.2-15B.Q3_K_S.gguf	Q3_K_S	6.21GB
L3-Stheno-v3.2-15B.IQ3_M.gguf	IQ3_M	6.43GB
L3-Stheno-v3.2-15B.Q3_K.gguf	Q3_K	6.87GB
L3-Stheno-v3.2-15B.Q3_K_M.gguf	Q3_K_M	6.87GB
L3-Stheno-v3.2-15B.Q3_K_L.gguf	Q3_K_L	7.43GB
L3-Stheno-v3.2-15B.IQ4_XS.gguf	IQ4_XS	7.68GB
L3-Stheno-v3.2-15B.Q4_0.gguf	Q4_0	8.0GB
L3-Stheno-v3.2-15B.IQ4_NL.gguf	IQ4_NL	8.08GB
L3-Stheno-v3.2-15B.Q4_K_S.gguf	Q4_K_S	8.05GB
L3-Stheno-v3.2-15B.Q4_K.gguf	Q4_K	8.48GB
L3-Stheno-v3.2-15B.Q4_K_M.gguf	Q4_K_M	8.48GB
L3-Stheno-v3.2-15B.Q4_1.gguf	Q4_1	8.84GB
L3-Stheno-v3.2-15B.Q5_0.gguf	Q5_0	9.68GB
L3-Stheno-v3.2-15B.Q5_K_S.gguf	Q5_K_S	9.68GB
L3-Stheno-v3.2-15B.Q5_K.gguf	Q5_K	9.93GB
L3-Stheno-v3.2-15B.Q5_K_M.gguf	Q5_K_M	9.93GB
L3-Stheno-v3.2-15B.Q5_1.gguf	Q5_1	10.53GB
L3-Stheno-v3.2-15B.Q6_K.gguf	Q6_K	11.48GB
L3-Stheno-v3.2-15B.Q8_0.gguf	Q8_0	14.86GB

Original model description:

base_model:

Sao10K/L3-8B-Stheno-v3.2

tags:

merge
mergekit
lazymergekit
Sao10K/L3-8B-Stheno-v3.2

L3-Stheno-v3.2-15B

L3-Stheno-v3.2-15B is a merge of the following models using LazyMergekit:

Credits to: Sao10K/L3-8B-Stheno-v3.2

🧩 Configuration

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 24]
    model: Sao10K/L3-8B-Stheno-v3.2
- sources:
  - layer_range: [8, 24]
    model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [8, 24]
    model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [24, 32]
    model: Sao10K/L3-8B-Stheno-v3.2

Created: Oct 6, 2024
Updated: Oct 7, 2024