You can deploy this model and start earning money today!

RichardErkhov/
grimjim_-_llama-3-merge-avalon-8B-gguf

Name: grimjim_-_llama-3-merge-avalon-8B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-merge-avalon-8B - GGUF

Model creator: https://huggingface.co/grimjim/
Original model: https://huggingface.co/grimjim/llama-3-merge-avalon-8B/

Name	Quant method	Size
llama-3-merge-avalon-8B.Q2_K.gguf	Q2_K	2.96GB
llama-3-merge-avalon-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
llama-3-merge-avalon-8B.IQ3_S.gguf	IQ3_S	3.43GB
llama-3-merge-avalon-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
llama-3-merge-avalon-8B.IQ3_M.gguf	IQ3_M	3.52GB
llama-3-merge-avalon-8B.Q3_K.gguf	Q3_K	3.74GB
llama-3-merge-avalon-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
llama-3-merge-avalon-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
llama-3-merge-avalon-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
llama-3-merge-avalon-8B.Q4_0.gguf	Q4_0	4.34GB
llama-3-merge-avalon-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
llama-3-merge-avalon-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
llama-3-merge-avalon-8B.Q4_K.gguf	Q4_K	4.58GB
llama-3-merge-avalon-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
llama-3-merge-avalon-8B.Q4_1.gguf	Q4_1	4.78GB
llama-3-merge-avalon-8B.Q5_0.gguf	Q5_0	5.21GB
llama-3-merge-avalon-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
llama-3-merge-avalon-8B.Q5_K.gguf	Q5_K	5.34GB
llama-3-merge-avalon-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
llama-3-merge-avalon-8B.Q5_1.gguf	Q5_1	5.65GB
llama-3-merge-avalon-8B.Q6_K.gguf	Q6_K	6.14GB
llama-3-merge-avalon-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

language:

en base_model:
grimjim/llama-3-merge-virt-req-8B
nbeerbower/llama-3-slerp-kraut-dragon-8B library_name: transformers tags:
meta
llama-3
pytorch
mergekit
merge license: cc-by-nc-4.0 pipeline_tag: text-generation

llama-3-merge-avalon-8B

This is a merge of pre-trained language models created using mergekit.

Lightly tested at temperature=1.0, minP=0.02 with provisional Llama 3 Instruct prompts.

Built with Meta Llama 3.

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:

yaml

slices:
  - sources:
    - model: grimjim/llama-3-merge-virt-req-8B
      layer_range: [0,32]
    - model: nbeerbower/llama-3-slerp-kraut-dragon-8B
      layer_range: [0,32]
merge_method: slerp
base_model: grimjim/llama-3-merge-virt-req-8B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

RichardErkhov/grimjim_-_llama-3-merge-avalon-8B-gguf