-
Hi, Is this any way to test your model as beam search?
I saw the code in train.py and agent.py ("beam_valid", "beam_search_test")
Could you please share any way to use it?
-
Hi everyone,
While evaluating the model, I got the following error:
`RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasLtMatmul( ltHandle, computeDesc.descriptor(), &alpha…
-
Hello @ruotianluo . I have three questions, and would appreciate an answer:
1- For running the transformer model If I would like to use beam search to evaluate after each epoch during training, sha…
-
### Describe the bug
Evaluating LibriSpeech `test-clean` can take >1h instead of something like two minutes.
I am not sure if this affects other models. Greedy search is much faster in comparison.…
-
请问如果我想使用旧版本的“internlm-xcomposer-7b”进行两张3090进行微调,应该如何修改代码。我发现最新的多卡运行代码无法适用旧版本的模型
-
I am that happy that beam search PR (https://github.com/vllm-project/vllm/pull/857) has been merged into main branch. But I tested 2 models ( llama2-7b and baichuan13b-base ) and found that they gener…
-
-
70B llama uses almost all vram and beam search new buffer allocation would fail due to out of resource.
It would be nice if we can search live with some flags to control buffer allocation. If not, …
-
right now, we're using beam search as an off-the-shelf component.
It would be great that:
* the search embeds some kind of patch quality knowledge: the first patch generated should have a better…
-
When I used the unigram subword method on Japanese, the WER got by fast_beam_search is expected, but when I used bpe subword, fast_beam_search got a lot of deletion errors as follows:
```
unigram:…