You can deploy this model and start earning money today!

RichardErkhov/
dumping-grounds_-_llama-3.1-minitron-6b-width-base-chatml-gguf

Name: dumping-grounds_-_llama-3.1-minitron-6b-width-base-chatml-gguf
Rating: 2.5 (268 reviews)

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3.1-minitron-6b-width-base-chatml - GGUF

Model creator: https://huggingface.co/dumping-grounds/
Original model: https://huggingface.co/dumping-grounds/llama-3.1-minitron-6b-width-base-chatml/

Name	Quant method	Size
llama-3.1-minitron-6b-width-base-chatml.Q2_K.gguf	Q2_K	2.36GB
llama-3.1-minitron-6b-width-base-chatml.IQ3_XS.gguf	IQ3_XS	2.6GB
llama-3.1-minitron-6b-width-base-chatml.IQ3_S.gguf	IQ3_S	2.72GB
llama-3.1-minitron-6b-width-base-chatml.Q3_K_S.gguf	Q3_K_S	2.7GB
llama-3.1-minitron-6b-width-base-chatml.IQ3_M.gguf	IQ3_M	2.82GB
llama-3.1-minitron-6b-width-base-chatml.Q3_K.gguf	Q3_K	2.97GB
llama-3.1-minitron-6b-width-base-chatml.Q3_K_M.gguf	Q3_K_M	2.97GB
llama-3.1-minitron-6b-width-base-chatml.Q3_K_L.gguf	Q3_K_L	3.21GB
llama-3.1-minitron-6b-width-base-chatml.IQ4_XS.gguf	IQ4_XS	3.32GB
llama-3.1-minitron-6b-width-base-chatml.Q4_0.gguf	Q4_0	3.44GB
llama-3.1-minitron-6b-width-base-chatml.IQ4_NL.gguf	IQ4_NL	3.48GB
llama-3.1-minitron-6b-width-base-chatml.Q4_K_S.gguf	Q4_K_S	3.46GB
llama-3.1-minitron-6b-width-base-chatml.Q4_K.gguf	Q4_K	3.62GB
llama-3.1-minitron-6b-width-base-chatml.Q4_K_M.gguf	Q4_K_M	3.62GB
llama-3.1-minitron-6b-width-base-chatml.Q4_1.gguf	Q4_1	3.79GB
llama-3.1-minitron-6b-width-base-chatml.Q5_0.gguf	Q5_0	4.14GB
llama-3.1-minitron-6b-width-base-chatml.Q5_K_S.gguf	Q5_K_S	4.14GB
llama-3.1-minitron-6b-width-base-chatml.Q5_K.gguf	Q5_K	4.23GB
llama-3.1-minitron-6b-width-base-chatml.Q5_K_M.gguf	Q5_K_M	4.23GB
llama-3.1-minitron-6b-width-base-chatml.Q5_1.gguf	Q5_1	4.49GB
llama-3.1-minitron-6b-width-base-chatml.Q6_K.gguf	Q6_K	4.88GB
llama-3.1-minitron-6b-width-base-chatml.Q8_0.gguf	Q8_0	6.32GB

Original model description:

base_model:

IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml library_name: transformers tags:
mergekit
merge

merge

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:

IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
        layer_range: [0, 24]
  - sources: # add middle layers with residuals scaled to zero
      - model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
        layer_range: [8, 24]
        parameters:
          scale:
            - filter: o_proj
              value: 0.0
            - filter: down_proj
              value: 0.0
            - value: 1.0
  - sources:
      - model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
        layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16

RichardErkhov/dumping-grounds_-_llama-3.1-minitron-6b-width-base-chatml-gguf