Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
julianmb
/
MiniCPM5-2B-NPU2
Like
4
Text Generation
English
Chinese
qwen3
fastflowlm
xdna2
npu
amd
strix-halo
strix-point
krackan
ryzen-ai
q4nx
rocm
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
2
Copy to bucket
new
main
MiniCPM5-2B-NPU2
2.03 GB
Ctrl+K
Ctrl+K
1 contributor
History:
23 commits
julianmb
docs: qualify runlist root-cause as hypothesis, correct QK-norm identity claim, add #716 attribution caveat
e3380c8
verified
1 day ago
.gitattributes
Safe
292 Bytes
Add .gitattributes
4 days ago
README.md
33.3 kB
docs: qualify runlist root-cause as hypothesis, correct QK-norm identity claim, add #716 attribution caveat
1 day ago
attn.xclbin
Safe
317 kB
xet
Add attn.xclbin
4 days ago
chat_template.jinja
Safe
9.06 kB
Add chat_template.jinja
4 days ago
config.json
Safe
883 Bytes
Add config.json
4 days ago
dequant.xclbin
Safe
114 kB
xet
Add dequant.xclbin
4 days ago
layer.xclbin
Safe
343 kB
xet
Add layer.xclbin
4 days ago
mm.xclbin
Safe
512 kB
xet
Add mm.xclbin
4 days ago
model.q4nx
Safe
2.02 GB
xet
Add model.q4nx weight tensors
4 days ago
special_tokens_map.json
Safe
551 Bytes
Add special_tokens_map.json
4 days ago
tokenizer.json
Safe
6.05 MB
Add tokenizer.json
4 days ago
tokenizer_config.json
Safe
94.5 kB
Fix tokenizer_config.json token IDs (bos/eos/pad) for FastFlowLM
4 days ago