RichardErkhov/Weyaxi_-_Einstein-v6.1-LLama3-8B-Instruct-Ties-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Einstein-v6.1-LLama3-8B-Instruct-Ties - GGUF

• Model creator: https://huggingface.co/Weyaxi/
• Original model: https://huggingface.co/Weyaxi/Einstein-v6.1-LLama3-8B-Instruct-Ties/

Name	Quant method	Size
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q2_K.gguf	Q2_K	2.96GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.IQ3_XS.gguf	IQ3_XS	3.28GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.IQ3_S.gguf	IQ3_S	3.43GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q3_K_S.gguf	Q3_K_S	3.41GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.IQ3_M.gguf	IQ3_M	3.52GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q3_K.gguf	Q3_K	3.74GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q3_K_M.gguf	Q3_K_M	3.74GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q3_K_L.gguf	Q3_K_L	4.03GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.IQ4_XS.gguf	IQ4_XS	4.18GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q4_0.gguf	Q4_0	4.34GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.IQ4_NL.gguf	IQ4_NL	4.38GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q4_K_S.gguf	Q4_K_S	4.37GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q4_K.gguf	Q4_K	4.58GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q4_K_M.gguf	Q4_K_M	4.58GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q4_1.gguf	Q4_1	4.78GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q5_0.gguf	Q5_0	5.21GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q5_K_S.gguf	Q5_K_S	5.21GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q5_K.gguf	Q5_K	5.34GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q5_K_M.gguf	Q5_K_M	5.34GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q5_1.gguf	Q5_1	5.65GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q6_K.gguf	Q6_K	6.14GB
Einstein-v6.1-LLama3-8B-Instruct-Ties.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: - Weyaxi/Einstein-v6.1-Llama3-8B - meta-llama/Meta-Llama-3-8B-Instruct - meta-llama/Meta-Llama-3-8B library_name: transformers tags: - mergekit - merge license: other

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using meta-llama/Meta-Llama-3-8B as a base.

Models Merged

The following models were included in the merge:

• Weyaxi/Einstein-v6.1-Llama3-8B
• meta-llama/Meta-Llama-3-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: meta-llama/Meta-Llama-3-8B
    #no parameters necessary for base model
  - model: Weyaxi/Einstein-v6.1-Llama3-8B
    parameters:
      density: 0.5
      weight: 0.5
  - model: meta-llama/Meta-Llama-3-8B-Instruct
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: meta-llama/Meta-Llama-3-8B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16