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
canada-quant
/
DeepSeek-V4-Flash-W4A16-FP8-MTP
like
0
Follow
Canada Quant Labs
3
Text Generation
Safetensors
vllm
deepseek_v4
deepseek
compressed-tensors
gptq
w4a16
fp8
mtp
speculative-decoding
conversational
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
DeepSeek-V4-Flash-W4A16-FP8-MTP
170 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
pastapaul
Add MMLU-Pro 71.28% (final extended benchmark)
a0dd15b
verified
about 14 hours ago
.gitattributes
Safe
1.52 kB
initial commit
1 day ago
README.md
13.6 kB
Add MMLU-Pro 71.28% (final extended benchmark)
about 14 hours ago
config.json
12.3 kB
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
generation_config.json
169 Bytes
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
model-00001-of-00004.safetensors
51.1 GB
xet
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
model-00002-of-00004.safetensors
50 GB
xet
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
model-00003-of-00004.safetensors
50 GB
xet
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
model-00004-of-00004.safetensors
18.8 GB
xet
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
model.safetensors.index.json
8.57 MB
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
recipe.yaml
2.06 kB
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
tokenizer.json
Safe
10.1 MB
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
tokenizer_config.json
Safe
397 Bytes
Phase 2 full GPTQ + BF16 MTP: 89.1% MTP acceptance
1 day ago
