Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
TroyDoesAI
/
MermaidMoE-15B
like
0
Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
MermaidMoE-15B
51.8 GB
1 contributor
History:
8 commits
TroyDoesAI
Update README.md
720ad77
verified
almost 2 years ago
.gitattributes
Safe
1.52 kB
initial commit
almost 2 years ago
README.md
Safe
159 Bytes
Update README.md
almost 2 years ago
added_tokens.json
Safe
21 Bytes
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
config.json
Safe
843 Bytes
Replaced Junk Layer with a more useful Layer, retraining still needed.
almost 2 years ago
generation_config.json
Safe
132 Bytes
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
model-00001-of-00005.safetensors
4.94 GB
xet
Upload 13 files
almost 2 years ago
model-00001-of-00007.safetensors
4.92 GB
xet
This is a fast 15B parameter 2x Self Merge MoE
almost 2 years ago
model-00002-of-00005.safetensors
5 GB
xet
Upload 13 files
almost 2 years ago
model-00002-of-00007.safetensors
5 GB
xet
This is a fast 15B parameter 2x Self Merge MoE
almost 2 years ago
model-00003-of-00005.safetensors
4.92 GB
xet
Upload 13 files
almost 2 years ago
model-00003-of-00007.safetensors
4.96 GB
xet
This is a fast 15B parameter 2x Self Merge MoE
almost 2 years ago
model-00004-of-00005.safetensors
4.92 GB
xet
Upload 13 files
almost 2 years ago
model-00004-of-00007.safetensors
4.87 GB
xet
This is a fast 15B parameter 2x Self Merge MoE
almost 2 years ago
model-00005-of-00005.safetensors
1.69 GB
xet
Upload 13 files
almost 2 years ago
model-00005-of-00007.safetensors
5 GB
xet
This is a fast 15B parameter 2x Self Merge MoE
almost 2 years ago
model-00006-of-00007.safetensors
4.96 GB
xet
This is a fast 15B parameter 2x Self Merge MoE
almost 2 years ago
model-00007-of-00007.safetensors
611 MB
xet
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
model.safetensors.index.json
Safe
32.9 kB
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
special_tokens_map.json
Safe
547 Bytes
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
tokenizer.json
Safe
1.84 MB
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
tokenizer.model
Safe
500 kB
xet
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
tokenizer_config.json
Safe
1.06 kB
Mixtral-2x12b ~ Very Experimental Architecture Choice By Self Evaluated Pruning Technique
almost 2 years ago
