You can deploy this model and start earning money today!

RichardErkhov/
choprahetarth_-_llama-it-merged-default_ties-gguf

Name: choprahetarth_-_llama-it-merged-default_ties-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-it-merged-default_ties - GGUF

Model creator: https://huggingface.co/choprahetarth/
Original model: https://huggingface.co/choprahetarth/llama-it-merged-default_ties/

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

Original model description:

base_model:

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

Untitled Model (1)

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:

meta-llama/Meta-Llama-3-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: meta-llama/Meta-Llama-3-8B
dtype: bfloat16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 32]
    model: meta-llama/Meta-Llama-3-8B
    parameters:
      density:
      - value: 0.5
      weight:
      - value: 0.5
  - layer_range: [0, 32]
    model: meta-llama/Meta-Llama-3-8B-Instruct
    parameters:
      density:
      - value: 0.5
      weight:
      - value: 0.5
tokenizer_source: union

RichardErkhov/choprahetarth_-_llama-it-merged-default_ties-gguf