Instructions to use jfrick/scholarly-code-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jfrick/scholarly-code-tokenizer with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jfrick/scholarly-code-tokenizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download research/structured-code-v1/tool-subtypes.json from jfrick/scholarly-code-tokenizer: direct link, hf CLI and curl.
- Browser
- Download file 15.8 kB
-
https://huggingface.co/jfrick/scholarly-code-tokenizer/resolve/main/research/structured-code-v1/tool-subtypes.json
- Command line
-
hf download hf://jfrick/scholarly-code-tokenizer/research/structured-code-v1/tool-subtypes.json
-
curl -L -o tool-subtypes.json https://huggingface.co/jfrick/scholarly-code-tokenizer/resolve/main/research/structured-code-v1/tool-subtypes.json
15.8 kB
| [ | |
| { | |
| "name": "original-64mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8595, | |
| "mean_tokens_per_example": 62.28260869565217 | |
| }, | |
| { | |
| "name": "original-64mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 37223, | |
| "mean_tokens_per_example": 310.19166666666666 | |
| }, | |
| { | |
| "name": "original-64mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 235899, | |
| "mean_tokens_per_example": 1760.4402985074628 | |
| }, | |
| { | |
| "name": "original-64mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 13373, | |
| "mean_tokens_per_example": 111.44166666666666 | |
| }, | |
| { | |
| "name": "original-64mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 9395, | |
| "mean_tokens_per_example": 68.07971014492753 | |
| }, | |
| { | |
| "name": "original-64mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 39947, | |
| "mean_tokens_per_example": 332.89166666666665 | |
| }, | |
| { | |
| "name": "original-64mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 254590, | |
| "mean_tokens_per_example": 1899.9253731343283 | |
| }, | |
| { | |
| "name": "original-64mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 14025, | |
| "mean_tokens_per_example": 116.875 | |
| }, | |
| { | |
| "name": "original-64mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8369, | |
| "mean_tokens_per_example": 60.64492753623188 | |
| }, | |
| { | |
| "name": "original-64mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 35332, | |
| "mean_tokens_per_example": 294.43333333333334 | |
| }, | |
| { | |
| "name": "original-64mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 227370, | |
| "mean_tokens_per_example": 1696.7910447761194 | |
| }, | |
| { | |
| "name": "original-64mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12785, | |
| "mean_tokens_per_example": 106.54166666666667 | |
| }, | |
| { | |
| "name": "original-128mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 9384, | |
| "mean_tokens_per_example": 68.0 | |
| }, | |
| { | |
| "name": "original-128mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 40035, | |
| "mean_tokens_per_example": 333.625 | |
| }, | |
| { | |
| "name": "original-128mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 253705, | |
| "mean_tokens_per_example": 1893.3208955223881 | |
| }, | |
| { | |
| "name": "original-128mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 13902, | |
| "mean_tokens_per_example": 115.85 | |
| }, | |
| { | |
| "name": "original-128mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8461, | |
| "mean_tokens_per_example": 61.31159420289855 | |
| }, | |
| { | |
| "name": "original-128mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 37017, | |
| "mean_tokens_per_example": 308.475 | |
| }, | |
| { | |
| "name": "original-128mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 235371, | |
| "mean_tokens_per_example": 1756.5 | |
| }, | |
| { | |
| "name": "original-128mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 13007, | |
| "mean_tokens_per_example": 108.39166666666667 | |
| }, | |
| { | |
| "name": "original-128mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8365, | |
| "mean_tokens_per_example": 60.61594202898551 | |
| }, | |
| { | |
| "name": "original-128mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 35323, | |
| "mean_tokens_per_example": 294.35833333333335 | |
| }, | |
| { | |
| "name": "original-128mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 227570, | |
| "mean_tokens_per_example": 1698.2835820895523 | |
| }, | |
| { | |
| "name": "original-128mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12805, | |
| "mean_tokens_per_example": 106.70833333333333 | |
| }, | |
| { | |
| "name": "original-256mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 9380, | |
| "mean_tokens_per_example": 67.97101449275362 | |
| }, | |
| { | |
| "name": "original-256mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 40021, | |
| "mean_tokens_per_example": 333.5083333333333 | |
| }, | |
| { | |
| "name": "original-256mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 253622, | |
| "mean_tokens_per_example": 1892.7014925373135 | |
| }, | |
| { | |
| "name": "original-256mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 13887, | |
| "mean_tokens_per_example": 115.725 | |
| }, | |
| { | |
| "name": "original-256mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8455, | |
| "mean_tokens_per_example": 61.268115942028984 | |
| }, | |
| { | |
| "name": "original-256mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 36954, | |
| "mean_tokens_per_example": 307.95 | |
| }, | |
| { | |
| "name": "original-256mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 234845, | |
| "mean_tokens_per_example": 1752.5746268656717 | |
| }, | |
| { | |
| "name": "original-256mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12998, | |
| "mean_tokens_per_example": 108.31666666666666 | |
| }, | |
| { | |
| "name": "original-512mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 9937, | |
| "mean_tokens_per_example": 72.0072463768116 | |
| }, | |
| { | |
| "name": "original-512mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 40599, | |
| "mean_tokens_per_example": 338.325 | |
| }, | |
| { | |
| "name": "original-512mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 253895, | |
| "mean_tokens_per_example": 1894.7388059701493 | |
| }, | |
| { | |
| "name": "original-512mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 14968, | |
| "mean_tokens_per_example": 124.73333333333333 | |
| }, | |
| { | |
| "name": "original-256mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8366, | |
| "mean_tokens_per_example": 60.6231884057971 | |
| }, | |
| { | |
| "name": "original-256mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 35267, | |
| "mean_tokens_per_example": 293.89166666666665 | |
| }, | |
| { | |
| "name": "original-256mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 226705, | |
| "mean_tokens_per_example": 1691.8283582089553 | |
| }, | |
| { | |
| "name": "original-256mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12799, | |
| "mean_tokens_per_example": 106.65833333333333 | |
| }, | |
| { | |
| "name": "original-512mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8446, | |
| "mean_tokens_per_example": 61.20289855072464 | |
| }, | |
| { | |
| "name": "original-512mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 36492, | |
| "mean_tokens_per_example": 304.1 | |
| }, | |
| { | |
| "name": "original-512mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 234429, | |
| "mean_tokens_per_example": 1749.4701492537313 | |
| }, | |
| { | |
| "name": "original-512mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 13004, | |
| "mean_tokens_per_example": 108.36666666666666 | |
| }, | |
| { | |
| "name": "original-512mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8360, | |
| "mean_tokens_per_example": 60.57971014492754 | |
| }, | |
| { | |
| "name": "original-512mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 35096, | |
| "mean_tokens_per_example": 292.46666666666664 | |
| }, | |
| { | |
| "name": "original-512mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 226557, | |
| "mean_tokens_per_example": 1690.7238805970148 | |
| }, | |
| { | |
| "name": "original-512mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12541, | |
| "mean_tokens_per_example": 104.50833333333334 | |
| }, | |
| { | |
| "name": "original-1024mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 9385, | |
| "mean_tokens_per_example": 68.0072463768116 | |
| }, | |
| { | |
| "name": "original-1024mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 40140, | |
| "mean_tokens_per_example": 334.5 | |
| }, | |
| { | |
| "name": "original-1024mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 253793, | |
| "mean_tokens_per_example": 1893.9776119402984 | |
| }, | |
| { | |
| "name": "original-1024mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 14005, | |
| "mean_tokens_per_example": 116.70833333333333 | |
| }, | |
| { | |
| "name": "original-1024mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8431, | |
| "mean_tokens_per_example": 61.094202898550726 | |
| }, | |
| { | |
| "name": "original-1024mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 36385, | |
| "mean_tokens_per_example": 303.2083333333333 | |
| }, | |
| { | |
| "name": "original-1024mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 234232, | |
| "mean_tokens_per_example": 1748.0 | |
| }, | |
| { | |
| "name": "original-1024mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12982, | |
| "mean_tokens_per_example": 108.18333333333334 | |
| }, | |
| { | |
| "name": "original-1024mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8358, | |
| "mean_tokens_per_example": 60.56521739130435 | |
| }, | |
| { | |
| "name": "original-1024mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 35108, | |
| "mean_tokens_per_example": 292.56666666666666 | |
| }, | |
| { | |
| "name": "original-1024mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 225118, | |
| "mean_tokens_per_example": 1679.9850746268658 | |
| }, | |
| { | |
| "name": "original-1024mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12780, | |
| "mean_tokens_per_example": 106.5 | |
| }, | |
| { | |
| "name": "original-2048mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 9380, | |
| "mean_tokens_per_example": 67.97101449275362 | |
| }, | |
| { | |
| "name": "original-2048mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 40089, | |
| "mean_tokens_per_example": 334.075 | |
| }, | |
| { | |
| "name": "original-2048mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 253445, | |
| "mean_tokens_per_example": 1891.3805970149253 | |
| }, | |
| { | |
| "name": "original-2048mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 14003, | |
| "mean_tokens_per_example": 116.69166666666666 | |
| }, | |
| { | |
| "name": "original-2048mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8361, | |
| "mean_tokens_per_example": 60.58695652173913 | |
| }, | |
| { | |
| "name": "original-2048mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 35220, | |
| "mean_tokens_per_example": 293.5 | |
| }, | |
| { | |
| "name": "original-2048mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 226049, | |
| "mean_tokens_per_example": 1686.9328358208954 | |
| }, | |
| { | |
| "name": "original-2048mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12769, | |
| "mean_tokens_per_example": 106.40833333333333 | |
| }, | |
| { | |
| "name": "original-2048mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 8443, | |
| "mean_tokens_per_example": 61.18115942028985 | |
| }, | |
| { | |
| "name": "original-2048mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 36917, | |
| "mean_tokens_per_example": 307.64166666666665 | |
| }, | |
| { | |
| "name": "original-2048mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 234319, | |
| "mean_tokens_per_example": 1748.6492537313434 | |
| }, | |
| { | |
| "name": "original-2048mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 12887, | |
| "mean_tokens_per_example": 107.39166666666667 | |
| }, | |
| { | |
| "name": "focused-64mib-16384", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 7389, | |
| "mean_tokens_per_example": 53.54347826086956 | |
| }, | |
| { | |
| "name": "focused-64mib-16384", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 32032, | |
| "mean_tokens_per_example": 266.93333333333334 | |
| }, | |
| { | |
| "name": "focused-64mib-16384", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 214219, | |
| "mean_tokens_per_example": 1598.6492537313434 | |
| }, | |
| { | |
| "name": "focused-64mib-16384", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 10136, | |
| "mean_tokens_per_example": 84.46666666666667 | |
| }, | |
| { | |
| "name": "focused-64mib-32768", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 7157, | |
| "mean_tokens_per_example": 51.86231884057971 | |
| }, | |
| { | |
| "name": "focused-64mib-32768", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 30871, | |
| "mean_tokens_per_example": 257.2583333333333 | |
| }, | |
| { | |
| "name": "focused-64mib-32768", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 203681, | |
| "mean_tokens_per_example": 1520.0074626865671 | |
| }, | |
| { | |
| "name": "focused-64mib-32768", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 9994, | |
| "mean_tokens_per_example": 83.28333333333333 | |
| }, | |
| { | |
| "name": "focused-64mib-50000", | |
| "kind": "read_file_call", | |
| "examples": 138, | |
| "bytes": 23364, | |
| "tokens": 7111, | |
| "mean_tokens_per_example": 51.528985507246375 | |
| }, | |
| { | |
| "name": "focused-64mib-50000", | |
| "kind": "apply_patch_call", | |
| "examples": 120, | |
| "bytes": 113181, | |
| "tokens": 30310, | |
| "mean_tokens_per_example": 252.58333333333334 | |
| }, | |
| { | |
| "name": "focused-64mib-50000", | |
| "kind": "tool_result", | |
| "examples": 134, | |
| "bytes": 780904, | |
| "tokens": 199176, | |
| "mean_tokens_per_example": 1486.3880597014925 | |
| }, | |
| { | |
| "name": "focused-64mib-50000", | |
| "kind": "schema_and_search_call", | |
| "examples": 120, | |
| "bytes": 48233, | |
| "tokens": 9946, | |
| "mean_tokens_per_example": 82.88333333333334 | |
| } | |
| ] | |