You can deploy this model and start earning money today!

RichardErkhov/
bhuvneshsaini_-_Llama-3.2-3B-merged-model-gguf

Name: bhuvneshsaini_-_Llama-3.2-3B-merged-model-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-3B-merged-model - GGUF

Model creator: https://huggingface.co/bhuvneshsaini/
Original model: https://huggingface.co/bhuvneshsaini/Llama-3.2-3B-merged-model/

Name	Quant method	Size
Llama-3.2-3B-merged-model.Q2_K.gguf	Q2_K	1.27GB
Llama-3.2-3B-merged-model.IQ3_XS.gguf	IQ3_XS	1.38GB
Llama-3.2-3B-merged-model.IQ3_S.gguf	IQ3_S	1.44GB
Llama-3.2-3B-merged-model.Q3_K_S.gguf	Q3_K_S	1.44GB
Llama-3.2-3B-merged-model.IQ3_M.gguf	IQ3_M	1.49GB
Llama-3.2-3B-merged-model.Q3_K.gguf	Q3_K	1.57GB
Llama-3.2-3B-merged-model.Q3_K_M.gguf	Q3_K_M	1.57GB
Llama-3.2-3B-merged-model.Q3_K_L.gguf	Q3_K_L	1.69GB
Llama-3.2-3B-merged-model.IQ4_XS.gguf	IQ4_XS	1.71GB
Llama-3.2-3B-merged-model.Q4_0.gguf	Q4_0	1.79GB
Llama-3.2-3B-merged-model.IQ4_NL.gguf	IQ4_NL	1.79GB
Llama-3.2-3B-merged-model.Q4_K_S.gguf	Q4_K_S	1.8GB
Llama-3.2-3B-merged-model.Q4_K.gguf	Q4_K	1.88GB
Llama-3.2-3B-merged-model.Q4_K_M.gguf	Q4_K_M	1.88GB
Llama-3.2-3B-merged-model.Q4_1.gguf	Q4_1	1.95GB
Llama-3.2-3B-merged-model.Q5_0.gguf	Q5_0	2.11GB
Llama-3.2-3B-merged-model.Q5_K_S.gguf	Q5_K_S	2.11GB
Llama-3.2-3B-merged-model.Q5_K.gguf	Q5_K	2.16GB
Llama-3.2-3B-merged-model.Q5_K_M.gguf	Q5_K_M	2.16GB
Llama-3.2-3B-merged-model.Q5_1.gguf	Q5_1	2.28GB
Llama-3.2-3B-merged-model.Q6_K.gguf	Q6_K	2.46GB
Llama-3.2-3B-merged-model.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model:

taareshg/unsloth-Llama-3.2-3B-Instruct-opus-Fr-En-merge
taareshg/unsloth-Llama-3.2-3B-Instruct-opus-En-Fr-merge 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 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: taareshg/unsloth-Llama-3.2-3B-Instruct-opus-Fr-En-merge
    layer_range:
    - 0
    - 28
  - model: taareshg/unsloth-Llama-3.2-3B-Instruct-opus-En-Fr-merge
    layer_range:
    - 0
    - 28
merge_method: slerp
base_model: taareshg/unsloth-Llama-3.2-3B-Instruct-opus-Fr-En-merge
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/bhuvneshsaini_-_Llama-3.2-3B-merged-model-gguf