You can deploy this model and start earning money today!

RichardErkhov/
Gunulhona_-_Phi-Small-Merge-gguf

Name: Gunulhona_-_Phi-Small-Merge-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-Small-Merge - GGUF

Model creator: https://huggingface.co/Gunulhona/
Original model: https://huggingface.co/Gunulhona/Phi-Small-Merge/

Name	Quant method	Size
Phi-Small-Merge.Q2_K.gguf	Q2_K	3.74GB
Phi-Small-Merge.IQ3_XS.gguf	IQ3_XS	4.31GB
Phi-Small-Merge.IQ3_S.gguf	IQ3_S	4.47GB
Phi-Small-Merge.Q3_K_S.gguf	Q3_K_S	4.47GB
Phi-Small-Merge.IQ3_M.gguf	IQ3_M	4.95GB
Phi-Small-Merge.Q3_K.gguf	Q3_K	5.23GB
Phi-Small-Merge.Q3_K_M.gguf	Q3_K_M	5.23GB
Phi-Small-Merge.Q3_K_L.gguf	Q3_K_L	5.6GB
Phi-Small-Merge.IQ4_XS.gguf	IQ4_XS	5.55GB
Phi-Small-Merge.Q4_0.gguf	Q4_0	5.83GB
Phi-Small-Merge.IQ4_NL.gguf	IQ4_NL	5.86GB
Phi-Small-Merge.Q4_K_S.gguf	Q4_K_S	5.86GB
Phi-Small-Merge.Q4_K.gguf	Q4_K	6.43GB
Phi-Small-Merge.Q4_K_M.gguf	Q4_K_M	6.43GB
Phi-Small-Merge.Q4_1.gguf	Q4_1	6.46GB
Phi-Small-Merge.Q5_0.gguf	Q5_0	7.1GB
Phi-Small-Merge.Q5_K_S.gguf	Q5_K_S	7.1GB
Phi-Small-Merge.Q5_K.gguf	Q5_K	7.59GB
Phi-Small-Merge.Q5_K_M.gguf	Q5_K_M	7.59GB
Phi-Small-Merge.Q5_1.gguf	Q5_1	7.74GB
Phi-Small-Merge.Q6_K.gguf	Q6_K	8.46GB
Phi-Small-Merge.Q8_0.gguf	Q8_0	10.96GB

Original model description:

base_model:

Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
jpacifico/Chocolatine-3B-Instruct-DPO-Revised
Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL 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: Antonio88/TaliML-PHI3-128K-ITA-V.1.0.FINAL
      layer_range: [0, 32]
  - sources:
    - model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
      layer_range: [0, 32]
  - sources:
    - model: Ejafa/phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
      layer_range: [0, 32]
base_model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
merge_method: slerp
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
  normalize: false
  int8_mask: true
  density: 0.7
  lambda: 1.1
  epsilon: 0.2
dtype: bfloat16

RichardErkhov/Gunulhona_-_Phi-Small-Merge-gguf