harpertoken commited on
Commit
3701a6c
·
verified ·
1 Parent(s): 4dd7ae0

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +18 -8
README.md CHANGED
@@ -22,17 +22,27 @@ Training used a learning rate of 2e-5 at batch size one for a single epoch, in f
22
 
23
  ## Usage
24
 
 
 
25
  ```python
26
- from transformers import pipeline
27
-
28
- qa = pipeline("question-answering", model="harpertoken/clue")
29
- answer = qa(
30
- question="What is the capital of France?",
31
- context="France is a country in Europe. Paris is its capital.",
32
- )
33
- print(answer["answer"], answer["score"])
 
 
 
 
 
 
34
  ```
35
 
 
 
36
  ## Limitations
37
 
38
  A thousand examples is a demonstration of the fine-tuning mechanics rather than a trained model, and the documentation this replaced claimed SQuAD exact-match and F1 figures that were never produced by an evaluation. Treat this as a low-fidelity copy of `quiz`. It is English-only, inherits the same uncased tokenisation and SQuAD domain bias described in the `quiz` card, and shares its 512-token limit. Compare the two directly before assuming the fine-tuning helped.
 
22
 
23
  ## Usage
24
 
25
+ Transformers 5 removed the `question-answering` pipeline, so load the model directly:
26
+
27
  ```python
28
+ import torch
29
+ from transformers import AutoModelForQuestionAnswering, AutoTokenizer
30
+
31
+ tok = AutoTokenizer.from_pretrained("harpertoken/clue")
32
+ model = AutoModelForQuestionAnswering.from_pretrained("harpertoken/clue")
33
+
34
+ question = "Who wrote Hamlet?"
35
+ context = "Hamlet is a tragedy written by William Shakespeare around 1600."
36
+ inputs = tok(question, context, return_tensors="pt", truncation=True, max_length=512)
37
+
38
+ with torch.inference_mode():
39
+ out = model(**inputs)
40
+ start, end = int(out.start_logits.argmax()), int(out.end_logits.argmax())
41
+ print(tok.decode(inputs.input_ids[0][start : end + 1]))
42
  ```
43
 
44
+ On the three questions used to check `quiz` — the capital of France, the author of Hamlet, and the year the Eiffel Tower was completed — this checkpoint returns `paris`, `william shakespeare` and `1889`, the same answers. A thousand examples has not visibly degraded it, which is itself a reason to doubt that the fine-tuning taught much.
45
+
46
  ## Limitations
47
 
48
  A thousand examples is a demonstration of the fine-tuning mechanics rather than a trained model, and the documentation this replaced claimed SQuAD exact-match and F1 figures that were never produced by an evaluation. Treat this as a low-fidelity copy of `quiz`. It is English-only, inherits the same uncased tokenisation and SQuAD domain bias described in the `quiz` card, and shares its 512-token limit. Compare the two directly before assuming the fine-tuning helped.