You can deploy this model and start earning money today!

RichardErkhov/
icefog72_-_LlamaIceCakeV0RP-3.1-8b-gguf

Name: icefog72_-_LlamaIceCakeV0RP-3.1-8b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LlamaIceCakeV0RP-3.1-8b - GGUF

Model creator: https://huggingface.co/icefog72/
Original model: https://huggingface.co/icefog72/LlamaIceCakeV0RP-3.1-8b/

Name	Quant method	Size
LlamaIceCakeV0RP-3.1-8b.Q2_K.gguf	Q2_K	2.96GB
LlamaIceCakeV0RP-3.1-8b.IQ3_XS.gguf	IQ3_XS	3.28GB
LlamaIceCakeV0RP-3.1-8b.IQ3_S.gguf	IQ3_S	3.43GB
LlamaIceCakeV0RP-3.1-8b.Q3_K_S.gguf	Q3_K_S	3.41GB
LlamaIceCakeV0RP-3.1-8b.IQ3_M.gguf	IQ3_M	3.52GB
LlamaIceCakeV0RP-3.1-8b.Q3_K.gguf	Q3_K	3.74GB
LlamaIceCakeV0RP-3.1-8b.Q3_K_M.gguf	Q3_K_M	3.74GB
LlamaIceCakeV0RP-3.1-8b.Q3_K_L.gguf	Q3_K_L	4.03GB
LlamaIceCakeV0RP-3.1-8b.IQ4_XS.gguf	IQ4_XS	4.18GB
LlamaIceCakeV0RP-3.1-8b.Q4_0.gguf	Q4_0	4.34GB
LlamaIceCakeV0RP-3.1-8b.IQ4_NL.gguf	IQ4_NL	4.38GB
LlamaIceCakeV0RP-3.1-8b.Q4_K_S.gguf	Q4_K_S	4.37GB
LlamaIceCakeV0RP-3.1-8b.Q4_K.gguf	Q4_K	4.58GB
LlamaIceCakeV0RP-3.1-8b.Q4_K_M.gguf	Q4_K_M	4.58GB
LlamaIceCakeV0RP-3.1-8b.Q4_1.gguf	Q4_1	4.78GB
LlamaIceCakeV0RP-3.1-8b.Q5_0.gguf	Q5_0	5.21GB
LlamaIceCakeV0RP-3.1-8b.Q5_K_S.gguf	Q5_K_S	5.21GB
LlamaIceCakeV0RP-3.1-8b.Q5_K.gguf	Q5_K	5.34GB
LlamaIceCakeV0RP-3.1-8b.Q5_K_M.gguf	Q5_K_M	5.34GB
LlamaIceCakeV0RP-3.1-8b.Q5_1.gguf	Q5_1	5.65GB
LlamaIceCakeV0RP-3.1-8b.Q6_K.gguf	Q6_K	6.14GB
LlamaIceCakeV0RP-3.1-8b.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: [] library_name: transformers tags:

mergekit
merge

IceCakeV0RP-3.1-8b

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:

D:\FModels\Meta-Llama-3.1-8B-Instruct
D:\FModels\modeltest8b3.1

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: D:\FModels\modeltest8b3.1
        layer_range: [0, 32]
      - model: D:\FModels\Meta-Llama-3.1-8B-Instruct
        layer_range: [0, 32]

merge_method: slerp
base_model: D:\FModels\Meta-Llama-3.1-8B-Instruct
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 # fallback for rest of tensors

dtype: bfloat16

RichardErkhov/icefog72_-_LlamaIceCakeV0RP-3.1-8b-gguf