Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
iamrahulreddy
/
Keiro
like
0
Text Generation
English
mixture-of-experts
sparse-moe
lora
qwen2.5
custom-architecture
causal-lm
conversational
arxiv:
1701.06538
arxiv:
2101.03961
arxiv:
2106.09685
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Keiro
245 MB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
iamrahulreddy
docs: sync README with Colab quickstart workflow
06cb25e
verified
about 1 month ago
architecture
fix: indendation error in config.py
about 1 month ago
.gitattributes
Safe
1.57 kB
add: Qwen2.5-3B tokenizer with ChatML template
about 1 month ago
README.md
Safe
13.8 kB
docs: sync README with Colab quickstart workflow
about 1 month ago
benchmark_report.png
Safe
53 kB
Upload benchmark_report.png
about 1 month ago
chat_template.jinja
Safe
199 Bytes
add: Qwen2.5-3B tokenizer with ChatML template
about 1 month ago
moe-best.pt
pickle
Detected Pickle imports (4)
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
234 MB
xet
add: Keiro MoE weights
about 1 month ago
tokenizer.json
Safe
11.4 MB
xet
add: Qwen2.5-3B tokenizer with ChatML template
about 1 month ago
tokenizer_config.json
Safe
668 Bytes
add: Qwen2.5-3B tokenizer with ChatML template
about 1 month ago