Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Spaces:

m97j
/

pragmatic-agent

Sleeping

App Files Files Community

Fetching metadata from the HF Docker repository...

pragmatic-agent / models

34.3 kB

Ctrl+K

Ctrl+K

2 contributors

History: 18 commits

m97j's picture

add decoding interface

fe9397b 4 months ago

decoding
add decoding interface 4 months ago
engines
feat(inference engine): add input normalization and attention_mask support 5 months ago
initializer.py

6.27 kB
feat(initializer): store prefix cache as input_ids tensors 5 months ago
llm_model.py

9.99 kB
fix(llm_model): align token chunking and prefix handling with engine 5 months ago
reranker_model.py

3.1 kB
fix: Modify code to ensure the input dtype/shape/key is what the ONNX model expects 5 months ago