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
aeonmind
/
DeepSeek-V4-Flash-UQFF-qtip2
like
0
Follow
Aeonmind, LLC
1
deepseek_v4
uqff
mistral.rs
arc
qtip2
fp8
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
DeepSeek-V4-Flash-UQFF-qtip2
74.2 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
heydryft
Correct the model card: working overlay invocation, public, measured GSM8K 96.0%
0b80b27
verified
1 day ago
.gitattributes
1.91 kB
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
README.md
11.2 kB
Correct the model card: working overlay invocation, public, measured GSM8K 96.0%
1 day ago
config.json
Safe
1.75 kB
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
generation_config.json
Safe
170 Bytes
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-0.uqff
10.3 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-1.uqff
10.4 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-2.uqff
10.3 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-3.uqff
10.3 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-4.uqff
10.3 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-5.uqff
10.3 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-6.uqff
10.3 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
qtip2-7.uqff
542 MB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
residual.safetensors
1.29 GB
xet
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
tokenizer.json
10.1 MB
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
tokenizer_config.json
Safe
801 Bytes
DeepSeek-V4-Flash UQFF qtip2 (beam W=256, hadamard-128, 43 layers)
2 days ago
