@huggingface/tasks 0.19.89 → 0.19.90

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (8) hide show
  1. package/dist/commonjs/eval.d.ts +7 -2
  2. package/dist/commonjs/eval.d.ts.map +1 -1
  3. package/dist/commonjs/eval.js +7 -2
  4. package/dist/esm/eval.d.ts +7 -2
  5. package/dist/esm/eval.d.ts.map +1 -1
  6. package/dist/esm/eval.js +7 -2
  7. package/package.json +1 -1
  8. package/src/eval.ts +8 -2
package/dist/commonjs/eval.d.ts CHANGED
@@ -17,8 +17,8 @@ export declare const EVALUATION_FRAMEWORKS: {
17
17
  readonly description: "Multimodal toolbox for evaluating embeddings and retrieval systems.";
18
18
  readonly url: "https://github.com/embeddings-benchmark/mteb";
19
19
  };
20
- readonly "olmo-bench": {
21
- readonly name: "olmo-bench";
20
+ readonly "olmocr-bench": {
21
+ readonly name: "olmocr-bench";
22
22
  readonly description: "olmOCR-Bench is a framework for evaluating document-level OCR of various tools.";
23
23
  readonly url: "https://github.com/allenai/olmocr/tree/main/olmocr/bench";
24
24
  };
@@ -42,5 +42,10 @@ export declare const EVALUATION_FRAMEWORKS: {
42
42
  readonly description: "SWE-Bench Pro is a challenging benchmark evaluating LLMs/Agents on long-horizon software engineering tasks.";
43
43
  readonly url: "https://github.com/scaleapi/SWE-bench_Pro-os";
44
44
  };
45
+ readonly "nemo-evaluator": {
46
+ readonly name: "nemo-evaluator";
47
+ readonly description: "NeMo Evaluator is an open-source platform for robust, reproducible, and scalable evaluation of Large Language Models across 100+ benchmarks.";
48
+ readonly url: "https://github.com/NVIDIA-NeMo/Evaluator";
49
+ };
45
50
  };
46
51
  //# sourceMappingURL=eval.d.ts.map
package/dist/commonjs/eval.d.ts.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"eval.d.ts","sourceRoot":"","sources":["../../src/eval.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA0CxB,CAAC"}
1
+ {"version":3,"file":"eval.d.ts","sourceRoot":"","sources":["../../src/eval.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAgDxB,CAAC"}
package/dist/commonjs/eval.js CHANGED
@@ -20,8 +20,8 @@ exports.EVALUATION_FRAMEWORKS = {
20
20
  description: "Multimodal toolbox for evaluating embeddings and retrieval systems.",
21
21
  url: "https://github.com/embeddings-benchmark/mteb",
22
22
  },
23
- "olmo-bench": {
24
- name: "olmo-bench",
23
+ "olmocr-bench": {
24
+ name: "olmocr-bench",
25
25
  description: "olmOCR-Bench is a framework for evaluating document-level OCR of various tools.",
26
26
  url: "https://github.com/allenai/olmocr/tree/main/olmocr/bench",
27
27
  },
@@ -45,4 +45,9 @@ exports.EVALUATION_FRAMEWORKS = {
45
45
  description: "SWE-Bench Pro is a challenging benchmark evaluating LLMs/Agents on long-horizon software engineering tasks.",
46
46
  url: "https://github.com/scaleapi/SWE-bench_Pro-os",
47
47
  },
48
+ "nemo-evaluator": {
49
+ name: "nemo-evaluator",
50
+ description: "NeMo Evaluator is an open-source platform for robust, reproducible, and scalable evaluation of Large Language Models across 100+ benchmarks.",
51
+ url: "https://github.com/NVIDIA-NeMo/Evaluator",
52
+ },
48
53
  };
package/dist/esm/eval.d.ts CHANGED
@@ -17,8 +17,8 @@ export declare const EVALUATION_FRAMEWORKS: {
17
17
  readonly description: "Multimodal toolbox for evaluating embeddings and retrieval systems.";
18
18
  readonly url: "https://github.com/embeddings-benchmark/mteb";
19
19
  };
20
- readonly "olmo-bench": {
21
- readonly name: "olmo-bench";
20
+ readonly "olmocr-bench": {
21
+ readonly name: "olmocr-bench";
22
22
  readonly description: "olmOCR-Bench is a framework for evaluating document-level OCR of various tools.";
23
23
  readonly url: "https://github.com/allenai/olmocr/tree/main/olmocr/bench";
24
24
  };
@@ -42,5 +42,10 @@ export declare const EVALUATION_FRAMEWORKS: {
42
42
  readonly description: "SWE-Bench Pro is a challenging benchmark evaluating LLMs/Agents on long-horizon software engineering tasks.";
43
43
  readonly url: "https://github.com/scaleapi/SWE-bench_Pro-os";
44
44
  };
45
+ readonly "nemo-evaluator": {
46
+ readonly name: "nemo-evaluator";
47
+ readonly description: "NeMo Evaluator is an open-source platform for robust, reproducible, and scalable evaluation of Large Language Models across 100+ benchmarks.";
48
+ readonly url: "https://github.com/NVIDIA-NeMo/Evaluator";
49
+ };
45
50
  };
46
51
  //# sourceMappingURL=eval.d.ts.map
package/dist/esm/eval.d.ts.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"eval.d.ts","sourceRoot":"","sources":["../../src/eval.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA0CxB,CAAC"}
1
+ {"version":3,"file":"eval.d.ts","sourceRoot":"","sources":["../../src/eval.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,eAAO,MAAM,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAgDxB,CAAC"}
package/dist/esm/eval.js CHANGED
@@ -17,8 +17,8 @@ export const EVALUATION_FRAMEWORKS = {
17
17
  description: "Multimodal toolbox for evaluating embeddings and retrieval systems.",
18
18
  url: "https://github.com/embeddings-benchmark/mteb",
19
19
  },
20
- "olmo-bench": {
21
- name: "olmo-bench",
20
+ "olmocr-bench": {
21
+ name: "olmocr-bench",
22
22
  description: "olmOCR-Bench is a framework for evaluating document-level OCR of various tools.",
23
23
  url: "https://github.com/allenai/olmocr/tree/main/olmocr/bench",
24
24
  },
@@ -42,4 +42,9 @@ export const EVALUATION_FRAMEWORKS = {
42
42
  description: "SWE-Bench Pro is a challenging benchmark evaluating LLMs/Agents on long-horizon software engineering tasks.",
43
43
  url: "https://github.com/scaleapi/SWE-bench_Pro-os",
44
44
  },
45
+ "nemo-evaluator": {
46
+ name: "nemo-evaluator",
47
+ description: "NeMo Evaluator is an open-source platform for robust, reproducible, and scalable evaluation of Large Language Models across 100+ benchmarks.",
48
+ url: "https://github.com/NVIDIA-NeMo/Evaluator",
49
+ },
45
50
  };
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@huggingface/tasks",
3
- "version": "0.19.89",
3
+ "version": "0.19.90",
4
4
  "description": "List of ML tasks for huggingface.co/tasks",
5
5
  "keywords": [
6
6
  "hub",
package/src/eval.ts CHANGED
@@ -17,8 +17,8 @@ export const EVALUATION_FRAMEWORKS = {
17
17
  description: "Multimodal toolbox for evaluating embeddings and retrieval systems.",
18
18
  url: "https://github.com/embeddings-benchmark/mteb",
19
19
  },
20
- "olmo-bench": {
21
- name: "olmo-bench",
20
+ "olmocr-bench": {
21
+ name: "olmocr-bench",
22
22
  description: "olmOCR-Bench is a framework for evaluating document-level OCR of various tools.",
23
23
  url: "https://github.com/allenai/olmocr/tree/main/olmocr/bench",
24
24
  },
@@ -43,4 +43,10 @@ export const EVALUATION_FRAMEWORKS = {
43
43
  "SWE-Bench Pro is a challenging benchmark evaluating LLMs/Agents on long-horizon software engineering tasks.",
44
44
  url: "https://github.com/scaleapi/SWE-bench_Pro-os",
45
45
  },
46
+ "nemo-evaluator": {
47
+ name: "nemo-evaluator",
48
+ description:
49
+ "NeMo Evaluator is an open-source platform for robust, reproducible, and scalable evaluation of Large Language Models across 100+ benchmarks.",
50
+ url: "https://github.com/NVIDIA-NeMo/Evaluator",
51
+ },
46
52
  } as const;