Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Bochkov
/
best_bvv_moe
like
0
Text Generation
Transformers
Safetensors
bvv_best
feature-extraction
causal-lm
russian
chinese
mixture-of-experts
frozen-embeddings
research
demonstration
low-resource
custom_code
arxiv:
2507.04886
arxiv:
2507.07129
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Train
Deploy
Use this model
main
best_bvv_moe
4.72 GB
2 contributors
History:
14 commits
Bochkov
Update README.md
b6ed48c
verified
17 days ago
.gitattributes
Safe
1.63 kB
Upload folder using huggingface_hub
5 months ago
README.md
Safe
4.96 kB
Update README.md
17 days ago
config.json
Safe
530 Bytes
Upload 3 files
5 months ago
embeddings_max.txt
Safe
404 MB
xet
Upload folder using huggingface_hub
5 months ago
merges.txt
Safe
1.48 MB
Upload folder using huggingface_hub
5 months ago
model.safetensors
3.76 GB
xet
Upload model.safetensors with huggingface_hub
5 months ago
modeling_bvv_best_moe.py
Safe
12.4 kB
Upload 3 files
5 months ago
normalized_embeddings_weights.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
537 MB
xet
Upload folder using huggingface_hub
5 months ago
special_tokens_map.json
Safe
95 Bytes
Upload folder using huggingface_hub
5 months ago
tokenizer.json
Safe
11.3 MB
xet
Upload folder using huggingface_hub
5 months ago
tokenizer_config.json
Safe
191 Bytes
Upload 3 files
5 months ago
vocab.json
Safe
2.35 MB
Upload folder using huggingface_hub
5 months ago
vocab.txt
Safe
4.19 MB
Upload folder using huggingface_hub
5 months ago