I’m trying to run prediction using CodeParrot . I’d like to use generate() because pipeline is too high-level but __call__ is too low-level: import transformers from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig tokenizer = AutoTokenizer.from_pretrained("codeparrot/c…

Using .generate() with CodeParrot

nelsonspbr April 15, 2023, 5:58pm 2

Having the same problem. It seems to be related to using GenerationConfig. Passing parameters directly to generate works fine.

Topic		Replies	Views
Unable to use model.generate for Vision encoder decoder model Beginners	3	1145	March 6, 2024
Always output generation config in terminal Models	1	253	November 15, 2023
How can I specify `stop_strings` in `generation_config.json`? 🤗Transformers	1	551	November 14, 2024
Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation Beginners	5	46276	September 24, 2024
Model.generate stop code execution without any error Beginners	0	716	May 26, 2023