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
model-00001-of-00017.safetensors 10.0 GBmodel-00010-of-00017.safetensors 10.0 GBmodel-00015-of-00017.safetensors 9.9 GBmodel-00016-of-00017.safetensors 9.9 GBmodel-00005-of-00017.safetensors 9.9 GBmodel-00006-of-00017.safetensors 9.9 GBmodel-00008-of-00017.safetensors 9.9 GBmodel-00009-of-00017.safetensors 9.9 GBmodel-00012-of-00017.safetensors 9.9 GBmodel-00013-of-00017.safetensors 9.9 GBmodel-00003-of-00017.safetensors 9.9 GBmodel-00011-of-00017.safetensors 9.9 GBmodel-00014-of-00017.safetensors 9.9 GBmodel-00007-of-00017.safetensors 9.9 GBmodel-00004-of-00017.safetensors 9.9 GBmodel-00002-of-00017.safetensors 9.9 GBmodel-00017-of-00017.safetensors 4.3 GBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Aratako/Mixtral-8x7B-Instruct-v0.1-upscaled ./model-foldermistralai/Mixtral-8x7B-Instruct-v0.1