Downloads · 30 days
142
5% of all-time downloads
RichardErkhov/Aratako_-_Mixtral-8x7B-Instruct-v0.1-upscaled-gguf
Aratako_-_Mixtral-8x7B-Instruct-v0.1-upscaled-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.
Downloads · 30 days
142
5% of all-time downloads
All-time downloads
2.6K
Public
Repo size
924 GB
Likes
0
Public
Click a slice to open those files.
.gguf1.1 TB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Mixtral-8x7B-Instruct-v0.1-upscaled - GGUF
base_model:
This is a frankenmerge of mistralai/Mixtral-8x7B-Instruct-v0.1 created by interleaving layers of itself using mergekit.
The benchmark score of the mt-bench for this model and the original models are as follows:
1-turn
| Model | Size | Coding | Extraction | Humanities | Math | Reasoning | Roleplay | STEM | Writing | avg_score |
|---|---|---|---|---|---|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1 | 8x7B | 5.3 | 8.5 | 9.9 | 6.8 | 6.0 | 9.1 | 9.55 | 8.9 | 8.00625 |
| This model | around 8x12B? | 6.3 | 8.4 | 9.9 | 5.4 | 7.7 | 9.2 | 9.75 | 9.8 | 8.30625 |

2-turn
| Model | Size | Coding | Extraction | Humanities | Math | Reasoning | Roleplay | STEM | Writing | avg_score |
|---|---|---|---|---|---|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1 | 8x7B | 4.1 | 8.4 | 9.8 | 4.7 | 5.6 | 9.0 | 9.2 | 9.5 | 7.5375 |
| This model | around 8x12B? | 4.2 | 7.4 | 9.9 | 4.0 | 5.2 | 9.5 | 8.7 | 8.0 | 7.1125 |

This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: passthrough
slices:
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [0, 8]
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [4, 12]
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [8, 16]
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [12, 20]
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [16, 24]
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [20, 28]
- sources:
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
layer_range: [24, 32]
dtype: bfloat16
tokenizer_source: base