lewtun HF staff commited on
Commit
a92816b
β€’
1 Parent(s): 5111f27
Files changed (3) hide show
  1. .github/workflows/sync_with_spaces.yml +1 -1
  2. README.md +26 -10
  3. app.py +2 -2
.github/workflows/sync_with_spaces.yml CHANGED
@@ -17,4 +17,4 @@ jobs:
17
  env:
18
  HF_TOKEN: ${{ secrets.HF_TOKEN }}
19
  run: |
20
- git push https://lewtun:[email protected]/spaces/autoevaluate/autoevaluate main
 
17
  env:
18
  HF_TOKEN: ${{ secrets.HF_TOKEN }}
19
  run: |
20
+ git push https://lewtun:[email protected]/spaces/autoevaluate/model-evaluator main
README.md CHANGED
@@ -8,7 +8,7 @@ sdk_version: 1.10.0
8
  app_file: app.py
9
  ---
10
 
11
- # AutoEvaluate
12
 
13
  > Submit evaluation jobs to AutoTrain from the Hugging Face Hub
14
 
@@ -16,12 +16,28 @@ app_file: app.py
16
 
17
  The table below shows which tasks are currently supported for evaluation in the AutoTrain backend:
18
 
19
- | Task | Supported | Sample prediction repository |
20
- |:--------------------------------|:---------:|:------------------------------------------------------------------------------------|
21
- | `binary_classification` | βœ… | [`eval-staging-835`](https://huggingface.co/datasets/autoevaluate/eval-staging-835) |
22
- | `multi_class_classification` | βœ… | [`eval-staging-822`](https://huggingface.co/datasets/autoevaluate/eval-staging-822) |
23
- | `multi_label_classification` | ❌ | |
24
- | `entity_extraction` | βœ… | [`eval-staging-838`](https://huggingface.co/datasets/autoevaluate/eval-staging-838) |
25
- | `extractive_question_answering` | βœ… | |
26
- | `translation` | βœ… | |
27
- | `summarization` | βœ… | |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  app_file: app.py
9
  ---
10
 
11
+ # Model Evaluator
12
 
13
  > Submit evaluation jobs to AutoTrain from the Hugging Face Hub
14
 
 
16
 
17
  The table below shows which tasks are currently supported for evaluation in the AutoTrain backend:
18
 
19
+ | Task | Supported |
20
+ |:-----------------------------------|:---------:|
21
+ | `binary_classification` | βœ… |
22
+ | `multi_class_classification` | βœ… |
23
+ | `multi_label_classification` | ❌ |
24
+ | `entity_extraction` | βœ… |
25
+ | `extractive_question_answering` | βœ… |
26
+ | `translation` | βœ… |
27
+ | `summarization` | βœ… |
28
+ | `image_binary_classification` | βœ… |
29
+ | `image_multi_class_classification` | βœ… |
30
+
31
+ ## Installation
32
+
33
+ To run the application, first clone this repository and install the dependencies as follows:
34
+
35
+ ```
36
+ pip install -r requirements.txt
37
+ ```
38
+
39
+ Then spin up the application by running:
40
+
41
+ ```
42
+ streamlit run app.py
43
+ ```
app.py CHANGED
@@ -161,7 +161,7 @@ is_valid_dataset = http_get(
161
  if is_valid_dataset["valid"] is False:
162
  st.error(
163
  """The dataset you selected is not currently supported. Open a \
164
- [discussion](https://huggingface.co/spaces/autoevaluate/autoevaluate/discussions) for support."""
165
  )
166
 
167
  metadata = get_metadata(selected_dataset)
@@ -176,7 +176,7 @@ with st.expander("Advanced configuration"):
176
  SUPPORTED_TASKS,
177
  index=SUPPORTED_TASKS.index(metadata[0]["task_id"]) if metadata is not None else 0,
178
  help="""Don't see your favourite task here? Open a \
179
- [discussion](https://huggingface.co/spaces/autoevaluate/autoevaluate/discussions) to request it!""",
180
  )
181
  # Select config
182
  configs = get_dataset_config_names(selected_dataset)
 
161
  if is_valid_dataset["valid"] is False:
162
  st.error(
163
  """The dataset you selected is not currently supported. Open a \
164
+ [discussion](https://huggingface.co/spaces/autoevaluate/model-evaluator/discussions) for support."""
165
  )
166
 
167
  metadata = get_metadata(selected_dataset)
 
176
  SUPPORTED_TASKS,
177
  index=SUPPORTED_TASKS.index(metadata[0]["task_id"]) if metadata is not None else 0,
178
  help="""Don't see your favourite task here? Open a \
179
+ [discussion](https://huggingface.co/spaces/autoevaluate/model-evaluator/discussions) to request it!""",
180
  )
181
  # Select config
182
  configs = get_dataset_config_names(selected_dataset)