You can deploy this model and start earning money today!

RichardErkhov/
ToastyPigeon_-_SmolLlama-1.5B-Sorted-gguf

Name: ToastyPigeon_-_SmolLlama-1.5B-Sorted-gguf
Availability: InStock

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SmolLlama-1.5B-Sorted - GGUF

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

Name	Quant method	Size
SmolLlama-1.5B-Sorted.Q2_K.gguf	Q2_K	0.55GB
SmolLlama-1.5B-Sorted.IQ3_XS.gguf	IQ3_XS	0.61GB
SmolLlama-1.5B-Sorted.IQ3_S.gguf	IQ3_S	0.64GB
SmolLlama-1.5B-Sorted.Q3_K_S.gguf	Q3_K_S	0.29GB
SmolLlama-1.5B-Sorted.IQ3_M.gguf	IQ3_M	0.29GB
SmolLlama-1.5B-Sorted.Q3_K.gguf	Q3_K	0.29GB
SmolLlama-1.5B-Sorted.Q3_K_M.gguf	Q3_K_M	0.29GB
SmolLlama-1.5B-Sorted.Q3_K_L.gguf	Q3_K_L	0.29GB
SmolLlama-1.5B-Sorted.IQ4_XS.gguf	IQ4_XS	0.79GB
SmolLlama-1.5B-Sorted.Q4_0.gguf	Q4_0	0.82GB
SmolLlama-1.5B-Sorted.IQ4_NL.gguf	IQ4_NL	0.83GB
SmolLlama-1.5B-Sorted.Q4_K_S.gguf	Q4_K_S	0.83GB
SmolLlama-1.5B-Sorted.Q4_K.gguf	Q4_K	0.87GB
SmolLlama-1.5B-Sorted.Q4_K_M.gguf	Q4_K_M	0.87GB
SmolLlama-1.5B-Sorted.Q4_1.gguf	Q4_1	0.91GB
SmolLlama-1.5B-Sorted.Q5_0.gguf	Q5_0	1.0GB
SmolLlama-1.5B-Sorted.Q5_K_S.gguf	Q5_K_S	1.0GB
SmolLlama-1.5B-Sorted.Q5_K.gguf	Q5_K	1.02GB
SmolLlama-1.5B-Sorted.Q5_K_M.gguf	Q5_K_M	1.02GB
SmolLlama-1.5B-Sorted.Q5_1.gguf	Q5_1	1.08GB
SmolLlama-1.5B-Sorted.Q6_K.gguf	Q6_K	1.18GB
SmolLlama-1.5B-Sorted.Q8_0.gguf	Q8_0	1.53GB

Original model description:

base_model: [] tags:

mergekit
merge license: apache-2.0

SmolLlama-1.5B-Sorted

Bigger than "Tiny" but still very smol.

This is a self-stack merge of TinyLlama 1.1B using a sorted-layer arrangement, resulting in 32 model layers and 1.54B model parameters.

In comparison to SmolLlama-1.5B, the Sorted version has the repeated middle layers placed in ascending order (see merge config).

This is a proof-of-concept model and should not be used for anything.

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:

yaml

slices:
  - sources: #non-repeating layers
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [0, 6]
  - sources: #begin repeating layers
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [6, 7]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [6, 7]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [7, 8]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [7, 8]
  - sources: 
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [8, 9]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [8, 9]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [9, 10]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [9, 10]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [10, 11]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [10, 11]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [11, 12]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [11, 12]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [12, 13]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [12, 13]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [13, 14]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [13, 14]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [14, 15]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [14, 15]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [15, 16]
  - sources:
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [15, 16]
  - sources: #non-repeating layers
    - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
      layer_range: [16, 22]
merge_method: passthrough
dtype: float16

RichardErkhov/ToastyPigeon_-_SmolLlama-1.5B-Sorted-gguf