Update README.md
Browse files
README.md
CHANGED
@@ -579,16 +579,4 @@ inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, ret
|
|
579 |
# tokenizer.eos_token_id is the id of <|EOT|> token
|
580 |
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
|
581 |
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
|
582 |
-
~~~
|
583 |
-
|
584 |
-
|
585 |
-
|
586 |
-
## References
|
587 |
-
- 1.Yan F, Mao H, Ji C C-J, et al. Berkeley Function Calling Leaderboard.
|
588 |
-
|
589 |
-
- 2. Abdelaziz I, Basu K, Agarwal M, et al. Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks[J]. arXiv preprint arXiv:2407.00121, 2024.
|
590 |
-
|
591 |
-
- 3. Wu M, Zhu T, Han H, et al. Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark[J]. arXiv preprint arXiv:2405.08355, 2024.
|
592 |
-
|
593 |
-
|
594 |
-
Feel free to reach out for further clarifications or contributions!
|
|
|
579 |
# tokenizer.eos_token_id is the id of <|EOT|> token
|
580 |
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
|
581 |
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
|
582 |
+
~~~
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|