You can deploy this model and start earning money today!

RichardErkhov/
Na0s_-_Llama-3.1-8b-Pruned-5-Layers-gguf

Name: Na0s_-_Llama-3.1-8b-Pruned-5-Layers-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.1-8b-Pruned-5-Layers - GGUF

Model creator: https://huggingface.co/Na0s/
Original model: https://huggingface.co/Na0s/Llama-3.1-8b-Pruned-5-Layers/

Name	Quant method	Size
Llama-3.1-8b-Pruned-5-Layers.Q2_K.gguf	Q2_K	2.51GB
Llama-3.1-8b-Pruned-5-Layers.IQ3_XS.gguf	IQ3_XS	2.78GB
Llama-3.1-8b-Pruned-5-Layers.IQ3_S.gguf	IQ3_S	2.9GB
Llama-3.1-8b-Pruned-5-Layers.Q3_K_S.gguf	Q3_K_S	2.89GB
Llama-3.1-8b-Pruned-5-Layers.IQ3_M.gguf	IQ3_M	2.98GB
Llama-3.1-8b-Pruned-5-Layers.Q3_K.gguf	Q3_K	3.15GB
Llama-3.1-8b-Pruned-5-Layers.Q3_K_M.gguf	Q3_K_M	3.15GB
Llama-3.1-8b-Pruned-5-Layers.Q3_K_L.gguf	Q3_K_L	3.39GB
Llama-3.1-8b-Pruned-5-Layers.IQ4_XS.gguf	IQ4_XS	3.52GB
Llama-3.1-8b-Pruned-5-Layers.Q4_0.gguf	Q4_0	3.66GB
Llama-3.1-8b-Pruned-5-Layers.IQ4_NL.gguf	IQ4_NL	3.69GB
Llama-3.1-8b-Pruned-5-Layers.Q4_K_S.gguf	Q4_K_S	3.68GB
Llama-3.1-8b-Pruned-5-Layers.Q4_K.gguf	Q4_K	3.85GB
Llama-3.1-8b-Pruned-5-Layers.Q4_K_M.gguf	Q4_K_M	3.85GB
Llama-3.1-8b-Pruned-5-Layers.Q4_1.gguf	Q4_1	4.02GB
Llama-3.1-8b-Pruned-5-Layers.Q5_0.gguf	Q5_0	4.38GB
Llama-3.1-8b-Pruned-5-Layers.Q5_K_S.gguf	Q5_K_S	4.38GB
Llama-3.1-8b-Pruned-5-Layers.Q5_K.gguf	Q5_K	4.48GB
Llama-3.1-8b-Pruned-5-Layers.Q5_K_M.gguf	Q5_K_M	4.48GB
Llama-3.1-8b-Pruned-5-Layers.Q5_1.gguf	Q5_1	4.74GB
Llama-3.1-8b-Pruned-5-Layers.Q6_K.gguf	Q6_K	5.14GB
Llama-3.1-8b-Pruned-5-Layers.Q8_0.gguf	Q8_0	6.66GB

Original model description:

base_model:

meta-llama/Meta-Llama-3.1-8B library_name: transformers tags:
mergekit
merge

Llama_3.1_8b_Pruned_5_Layers

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:

meta-llama/Meta-Llama-3.1-8B

Configuration

The following YAML configuration was used to produce this model:

yaml

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 22]
    model: meta-llama/Meta-Llama-3.1-8B
- sources:
  - layer_range: [28, 32]
    model: meta-llama/Meta-Llama-3.1-8B

RichardErkhov/Na0s_-_Llama-3.1-8b-Pruned-5-Layers-gguf