Spaces:

visualisable-ai
/

api

Running on CPU Upgrade

App Files Files Community

api / backend

330 kB

3 contributors

History: 35 commits

gary-boon

Add vocabSize to modelInfo response

499afba 3 days ago

Dockerfile

460 Bytes

Fix backend structure - remove duplicates 4 months ago
architectural_analysis.py

10.6 kB

Add research attention analysis endpoints with Q/K/V extraction about 1 month ago
attention_analysis.py

16.8 kB

Add research attention analysis endpoints with Q/K/V extraction about 1 month ago
auth.py

1.18 kB

Fix backend structure - remove duplicates 4 months ago
context_efficiency_analyzer.py

13.4 kB

Add backend support for ICL emergence analysis 4 months ago
icl_attention_extractor.py

11.4 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes about 2 months ago
icl_service.py

13.2 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes about 2 months ago
induction_head_detector.py

13.8 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes about 2 months ago
instrumentation.py

15.9 kB

Add research attention analysis endpoints with Q/K/V extraction about 1 month ago
model_adapter.py

11 kB

Phase 2: Add Devstral backend support 4 days ago
model_config.py

4.3 kB

Add recommended_dtype to model configs 4 days ago
model_service.py

113 kB

Add vocabSize to modelInfo response 3 days ago
pipeline_analyzer.py

29 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes about 2 months ago
qkv_extractor.py

20.7 kB

Add Code Llama 7B support with hardware-aware filtering and ICL timeout fixes about 2 months ago
requirements.txt

166 Bytes

Fix backend structure - remove duplicates 4 months ago
storage.py

12.4 kB

Make zarr/numcodecs imports optional for ARM64 compatibility 4 days ago
swe_bench_service.py

18.6 kB

Fix pyarrow compatibility issue with datasets library 3 months ago
test_ablation.py

15.6 kB

Add ablation support to model service with comprehensive testing 4 months ago
tokenizer_utils.py

8.61 kB

Add research attention analysis endpoints with Q/K/V extraction about 1 month ago