Feature Extraction
Safetensors
ColPali
English
colpali-engine
colqwen2_5
colqwen
multi-vector
late-interaction
visual-document-retrieval
document-ai
quantization
maxsim
Instructions to use Adityapande403/VisDoc-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use Adityapande403/VisDoc-AI with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download retrieval_benchmark.json from Adityapande403/VisDoc-AI: direct link, hf CLI and curl.
- Browser
- Download file 2.84 kB
-
https://huggingface.co/Adityapande403/VisDoc-AI/resolve/main/retrieval_benchmark.json
- Command line
-
hf download hf://Adityapande403/VisDoc-AI/retrieval_benchmark.json
-
curl -L -o retrieval_benchmark.json https://huggingface.co/Adityapande403/VisDoc-AI/resolve/main/retrieval_benchmark.json
2.84 kB
| { | |
| "fp16": { | |
| "format": "fp16", | |
| "metrics": { | |
| "ndcg@5": 0.5132314787418083, | |
| "mrr@10": 0.4361111111111111, | |
| "recall@1": 0.16666666666666666, | |
| "recall@5": 0.8333333333333334, | |
| "recall@10": 1.0, | |
| "recall@20": 1.0, | |
| "evaluated_queries": 6 | |
| }, | |
| "retention": 1.0, | |
| "latency_stats": { | |
| "mean_ms": 1.4175499964039773, | |
| "median_ms": 1.396150008076802, | |
| "p90_ms": 1.5272499877028167, | |
| "p95_ms": 1.5332250040955842, | |
| "p99_ms": 1.538005017209798 | |
| }, | |
| "memory_stats": { | |
| "format": "fp16", | |
| "total_pages": 6, | |
| "total_vectors": 384, | |
| "quantized_embedding_bytes": 98304, | |
| "quantized_embedding_mb": 0.09375, | |
| "summary_bytes": 3072, | |
| "summary_mb": 0.0029296875, | |
| "fp16_baseline_mb": 0.09375, | |
| "compression_ratio_vs_fp16": 1.0, | |
| "compression_ratio_vs_fp32": 2.0, | |
| "device": "cuda" | |
| } | |
| }, | |
| "int8": { | |
| "format": "int8", | |
| "metrics": { | |
| "ndcg@5": 0.5132314787418083, | |
| "mrr@10": 0.4361111111111111, | |
| "recall@1": 0.16666666666666666, | |
| "recall@5": 0.8333333333333334, | |
| "recall@10": 1.0, | |
| "recall@20": 1.0, | |
| "evaluated_queries": 6 | |
| }, | |
| "retention": 1.0, | |
| "latency_stats": { | |
| "mean_ms": 1.978349998050059, | |
| "median_ms": 1.978349988348782, | |
| "p90_ms": 2.0354499865788966, | |
| "p95_ms": 2.036524980212562, | |
| "p99_ms": 2.037384975119494 | |
| }, | |
| "memory_stats": { | |
| "format": "int8", | |
| "total_pages": 6, | |
| "total_vectors": 384, | |
| "quantized_embedding_bytes": 49152, | |
| "quantized_embedding_mb": 0.046875, | |
| "summary_bytes": 3072, | |
| "summary_mb": 0.0029296875, | |
| "fp16_baseline_mb": 0.09375, | |
| "compression_ratio_vs_fp16": 2.0, | |
| "compression_ratio_vs_fp32": 4.0, | |
| "device": "cuda" | |
| } | |
| }, | |
| "binary": { | |
| "format": "binary", | |
| "metrics": { | |
| "ndcg@5": 0.3747009872302213, | |
| "mrr@10": 0.25555555555555554, | |
| "recall@1": 0.0, | |
| "recall@5": 0.8333333333333334, | |
| "recall@10": 1.0, | |
| "recall@20": 1.0, | |
| "evaluated_queries": 6 | |
| }, | |
| "retention": 0.7300818495171112, | |
| "latency_stats": { | |
| "mean_ms": 1.8759666612216581, | |
| "median_ms": 1.7842999659478664, | |
| "p90_ms": 2.1018999977968633, | |
| "p95_ms": 2.1988000080455095, | |
| "p99_ms": 2.2763200162444264 | |
| }, | |
| "memory_stats": { | |
| "format": "binary", | |
| "total_pages": 6, | |
| "total_vectors": 384, | |
| "quantized_embedding_bytes": 6144, | |
| "quantized_embedding_mb": 0.005859375, | |
| "summary_bytes": 3072, | |
| "summary_mb": 0.0029296875, | |
| "fp16_baseline_mb": 0.09375, | |
| "compression_ratio_vs_fp16": 16.0, | |
| "compression_ratio_vs_fp32": 32.0, | |
| "device": "cuda" | |
| } | |
| } | |
| } |