Downloads · 30 days
65
5% of all-time downloads
zelus82_-_Obelix-Phi2-gguf
RichardErkhov/zelus82_-_Obelix-Phi2-gguf
zelus82_-_Obelix-Phi2-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
1.4K
Public
Repo size
32.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf37.4 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 6, 2024
- Updated
- Oct 6, 2024
- SHA
- 9bd3e843
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Obelix-Phi2 - GGUF
- Model creator: https://huggingface.co/zelus82/
- Original model: https://huggingface.co/zelus82/Obelix-Phi2/
| Name | Quant method | Size |
|---|---|---|
| Obelix-Phi2.Q2_K.gguf | Q2_K | 1.03GB |
| Obelix-Phi2.IQ3_XS.gguf | IQ3_XS | 1.12GB |
| Obelix-Phi2.IQ3_S.gguf | IQ3_S | 1.16GB |
| Obelix-Phi2.Q3_K_S.gguf | Q3_K_S | 1.16GB |
| Obelix-Phi2.IQ3_M.gguf | IQ3_M | 1.23GB |
| Obelix-Phi2.Q3_K.gguf | Q3_K | 1.33GB |
| Obelix-Phi2.Q3_K_M.gguf | Q3_K_M | 1.33GB |
| Obelix-Phi2.Q3_K_L.gguf | Q3_K_L | 1.47GB |
| Obelix-Phi2.IQ4_XS.gguf | IQ4_XS | 1.43GB |
| Obelix-Phi2.Q4_0.gguf | Q4_0 | 1.49GB |
| Obelix-Phi2.IQ4_NL.gguf | IQ4_NL | 1.5GB |
| Obelix-Phi2.Q4_K_S.gguf | Q4_K_S | 1.51GB |
| Obelix-Phi2.Q4_K.gguf | Q4_K | 1.62GB |
| Obelix-Phi2.Q4_K_M.gguf | Q4_K_M | 1.62GB |
| Obelix-Phi2.Q4_1.gguf | Q4_1 | 1.65GB |
| Obelix-Phi2.Q5_0.gguf | Q5_0 | 1.8GB |
| Obelix-Phi2.Q5_K_S.gguf | Q5_K_S | 1.8GB |
| Obelix-Phi2.Q5_K.gguf | Q5_K | 1.87GB |
| Obelix-Phi2.Q5_K_M.gguf | Q5_K_M | 1.87GB |
| Obelix-Phi2.Q5_1.gguf | Q5_1 | 1.95GB |
| Obelix-Phi2.Q6_K.gguf | Q6_K | 2.13GB |
| Obelix-Phi2.Q8_0.gguf | Q8_0 | 2.75GB |
Original model description:
base_model:
- abacaj/phi-2-super
- rhysjones/phi-2-orange-v2 library_name: transformers tags:
- mergekit
- merge license: apache-2.0
<img src="Obelix.jpeg"> # merged_folders
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:
slices:
- sources:
- model: abacaj/phi-2-super
layer_range: [0, 32]
- model: rhysjones/phi-2-orange-v2
layer_range: [0, 32]
merge_method: slerp
base_model: abacaj/phi-2-super
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
- Created
- Oct 6, 2024
- Updated
- Oct 6, 2024