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
canada-quant
/
hy3-w4a16-mtp
like
4
Follow
Canada Quant Labs
32
Text Generation
Safetensors
5 datasets
English
Chinese
vllm
hy_v3
hy3
hunyuan
w4a16
gptq
int4
compressed-tensors
Mixture of Experts
mixture-of-experts
mtp
speculative-decoding
llmcompressor
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
hy3-w4a16-mtp
173 GB
Ctrl+K
Ctrl+K
1 contributor
History:
11 commits
pastapaul
Fix calibration dataset metadata: reflect actual code+math+chat blend + link published calibration set
49228b9
verified
14 days ago
findings
docs: findings referenced by the model card (fixes 404 links)
15 days ago
.gitattributes
Safe
1.58 kB
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
README.md
18.1 kB
Fix calibration dataset metadata: reflect actual code+math+chat blend + link published calibration set
14 days ago
chat_template.jinja
Safe
10.2 kB
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
chat_template_high.jinja
Safe
10.2 kB
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
config.json
Safe
31.4 kB
Upload config.json with huggingface_hub
16 days ago
deploy-hopper.md
3.59 kB
deploy guide: measured 4xH100 256K validation
15 days ago
generation_config.json
189 Bytes
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
model-00001-of-00004.safetensors
50 GB
xet
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
model-00002-of-00004.safetensors
50 GB
xet
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
model-00003-of-00004.safetensors
50 GB
xet
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
model-00004-of-00004.safetensors
15.1 GB
xet
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
model-mtp.safetensors
7.51 GB
xet
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
model.safetensors.index.json
13.4 MB
xet
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
recipe.yaml
935 Bytes
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
tokenizer.json
9.53 MB
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago
tokenizer_config.json
Safe
396 Bytes
release: Hy3 W4A16-MTP weights (verified artifact, 172GB)
15 days ago