ToastyPigeon_-_SmolLlama-1.5B-gguf

RichardErkhov/ToastyPigeon_-_SmolLlama-1.5B-gguf

ToastyPigeon_-_SmolLlama-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

396

7% of all-time downloads

All-time downloads

5.8K

Public

Repo size

17.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf20.4 GB · 100%

At a glance

Access: Public
Created: Jun 24, 2024
Updated: Jun 24, 2024
SHA: fde80bbb

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SmolLlama-1.5B - GGUF

Model creator: https://huggingface.co/ToastyPigeon/
Original model: https://huggingface.co/ToastyPigeon/SmolLlama-1.5B/

Name	Quant method	Size
SmolLlama-1.5B.Q2_K.gguf	Q2_K	0.55GB
SmolLlama-1.5B.IQ3_XS.gguf	IQ3_XS	0.61GB
SmolLlama-1.5B.IQ3_S.gguf	IQ3_S	0.64GB
SmolLlama-1.5B.Q3_K_S.gguf	Q3_K_S	0.64GB
SmolLlama-1.5B.IQ3_M.gguf	IQ3_M	0.67GB
SmolLlama-1.5B.Q3_K.gguf	Q3_K	0.71GB
SmolLlama-1.5B.Q3_K_M.gguf	Q3_K_M	0.71GB
SmolLlama-1.5B.Q3_K_L.gguf	Q3_K_L	0.77GB
SmolLlama-1.5B.IQ4_XS.gguf	IQ4_XS	0.79GB
SmolLlama-1.5B.Q4_0.gguf	Q4_0	0.82GB
SmolLlama-1.5B.IQ4_NL.gguf	IQ4_NL	0.83GB
SmolLlama-1.5B.Q4_K_S.gguf	Q4_K_S	0.83GB
SmolLlama-1.5B.Q4_K.gguf	Q4_K	0.87GB
SmolLlama-1.5B.Q4_K_M.gguf	Q4_K_M	0.87GB
SmolLlama-1.5B.Q4_1.gguf	Q4_1	0.91GB
SmolLlama-1.5B.Q5_0.gguf	Q5_0	1.0GB
SmolLlama-1.5B.Q5_K_S.gguf	Q5_K_S	1.0GB
SmolLlama-1.5B.Q5_K.gguf	Q5_K	1.02GB
SmolLlama-1.5B.Q5_K_M.gguf	Q5_K_M	1.02GB
SmolLlama-1.5B.Q5_1.gguf	Q5_1	1.08GB
SmolLlama-1.5B.Q6_K.gguf	Q6_K	1.18GB
SmolLlama-1.5B.Q8_0.gguf	Q8_0	1.53GB

Original model description:

base_model: [] tags:

mergekit
merge license: apache-2.0

SmolLlama-1.5B

Bigger than "Tiny" but still very smol.

Self-stack of TinyLlama 1.1B using a SOLAR-style cut, resulting in 32 layers and 1.54B model parameters.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources: 
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [0, 16]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [6, 22]
merge_method: passthrough
dtype: float16

Created: Jun 24, 2024
Updated: Jun 24, 2024