You can deploy this model and start earning money today!

RichardErkhov/
thucdangvan020999_-_llama3.1_6.5b_mergkit_prunme-gguf

Name: thucdangvan020999_-_llama3.1_6.5b_mergkit_prunme-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3.1_6.5b_mergkit_prunme - GGUF

Model creator: https://huggingface.co/thucdangvan020999/
Original model: https://huggingface.co/thucdangvan020999/llama3.1_6.5b_mergkit_prunme/

Name	Quant method	Size
llama3.1_6.5b_mergkit_prunme.Q2_K.gguf	Q2_K	2.44GB
llama3.1_6.5b_mergkit_prunme.Q3_K_S.gguf	Q3_K_S	2.8GB
llama3.1_6.5b_mergkit_prunme.Q3_K.gguf	Q3_K	3.06GB
llama3.1_6.5b_mergkit_prunme.Q3_K_M.gguf	Q3_K_M	3.06GB
llama3.1_6.5b_mergkit_prunme.Q3_K_L.gguf	Q3_K_L	3.28GB
llama3.1_6.5b_mergkit_prunme.IQ4_XS.gguf	IQ4_XS	3.41GB
llama3.1_6.5b_mergkit_prunme.Q4_0.gguf	Q4_0	3.54GB
llama3.1_6.5b_mergkit_prunme.IQ4_NL.gguf	IQ4_NL	3.57GB
llama3.1_6.5b_mergkit_prunme.Q4_K_S.gguf	Q4_K_S	3.56GB
llama3.1_6.5b_mergkit_prunme.Q4_K.gguf	Q4_K	3.74GB
llama3.1_6.5b_mergkit_prunme.Q4_K_M.gguf	Q4_K_M	3.74GB
llama3.1_6.5b_mergkit_prunme.Q4_1.gguf	Q4_1	3.89GB
llama3.1_6.5b_mergkit_prunme.Q5_0.gguf	Q5_0	4.24GB
llama3.1_6.5b_mergkit_prunme.Q5_K_S.gguf	Q5_K_S	4.24GB
llama3.1_6.5b_mergkit_prunme.Q5_K.gguf	Q5_K	4.34GB
llama3.1_6.5b_mergkit_prunme.Q5_K_M.gguf	Q5_K_M	4.34GB
llama3.1_6.5b_mergkit_prunme.Q5_1.gguf	Q5_1	4.58GB
llama3.1_6.5b_mergkit_prunme.Q6_K.gguf	Q6_K	4.98GB
llama3.1_6.5b_mergkit_prunme.Q8_0.gguf	Q8_0	6.44GB

Original model description:

base_model:

meta-llama/Meta-Llama-3-8B-Instruct library_name: transformers tags:
mergekit
merge

merged

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-3-8B-Instruct

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-3-8B-Instruct
- sources:
  - layer_range: [29, 32]
    model: meta-llama/Meta-Llama-3-8B-Instruct

RichardErkhov/thucdangvan020999_-_llama3.1_6.5b_mergkit_prunme-gguf