Downloads · 30 days
56
12% of all-time downloads
Gunulhona_-_Phi-Small-Merge-gguf
RichardErkhov/Gunulhona_-_Phi-Small-Merge-gguf
Gunulhona_-_Phi-Small-Merge-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
476
Public
Repo size
126 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf147 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 2, 2024
- Updated
- Oct 3, 2024
- SHA
- 62324c6c
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
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:
- 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
Configuration
The following YAML configuration was used to produce this model:
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
- Created
- Oct 2, 2024
- Updated
- Oct 3, 2024