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
justinchuby
/
onnx-genai-example-gemma4-e2b-assistant
like
0
Text Generation
ONNX
onnxruntime
gemma4
speculative-decoding
draft-model
inference-metadata
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
onnx-genai-example-gemma4-e2b-assistant
10.7 GB
Ctrl+K
Ctrl+K
1 contributor
History:
14 commits
justinchuby
Add target assets required by speculative metadata
27f03dd
verified
6 days ago
evidence
Explicit folded_carry_seed/token_embedding for the final #1716 chained schema
11 days ago
target
Add target assets required by speculative metadata
6 days ago
.gitattributes
Safe
1.62 kB
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
METADATA_STATUS.md
Safe
6.49 kB
Speculative inference_metadata.yaml now passes the authoritative #1716 Rust validator: alias keys = borrowed owner cells, folded_carry_output, distribution_preserving=true, identical vocab, combined-package layout (target/model.onnx)
11 days ago
README.md
Safe
5.81 kB
Add annotated inference metadata companion
7 days ago
SOURCE_LICENSE.md
Safe
341 Bytes
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
component_contract.json
Safe
4.01 kB
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
component_contract.yaml
Safe
3.26 kB
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
file_sizes.tsv
Safe
809 Bytes
Finalize speculative metadata: read_only anchor cells = last owners (14/13), shared_weights=[model.embed_tokens.weight]; generator now self-runs the authoritative Rust validator
11 days ago
inference_metadata.annotated.yaml
Safe
156 kB
Add annotated inference metadata companion
7 days ago
inference_metadata.yaml
Safe
54.3 kB
Explicit folded_carry_seed/token_embedding for the final #1716 chained schema
11 days ago
model.onnx
Safe
81.9 kB
xet
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
model.onnx.data
Safe
359 MB
xet
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
package_size_bytes.txt
Safe
10 Bytes
Finalize speculative metadata: read_only anchor cells = last owners (14/13), shared_weights=[model.embed_tokens.weight]; generator now self-runs the authoritative Rust validator
11 days ago
performance.json
Safe
718 Bytes
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
publication_verification.json
Safe
463 Bytes
Refresh publication_verification.json (post hidden_states.34 republish)
11 days ago
runtime_versions.json
Safe
575 Bytes
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
source_provenance.json
Safe
2.23 kB
Explicit folded_carry_seed/token_embedding for the final #1716 chained schema
11 days ago
tokenizer.json
Safe
32.2 MB
xet
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago
tokenizer_config.json
Safe
822 Bytes
Add Gemma-4 E2B-it assistant drafter (fp16 CUDA) + faithful component contract + L4/L5 parity
11 days ago