-
已连接到 pydev 调试器(内部版本号 221.5787.24)09/02/2024 19:33:36 - INFO - easyeditor.trainer.BaseTrainer - Config: SERACMultimodalTrainingHparams(qformer_name_or_path='bert-base-uncased', state_dict_file='huggi…
-
Sentiment analysis as a key to (re)generation/modifric[a]tion?
Templates up the Wazoo (the rebranding as "Templates 2.0" just didn't catch on)?
Good Ol' Markov, but weighted with positioning (beginn…
-
### What is your question?
Hello, I'm trying to use google gemini but don't know what I'm doing wrong.
I'm running the follow commands
```
(base) mruserbox@guru-X99:/home/guru/Desktop/GURU_PROJE…
-
Hello, I encounter the error "RuntimeError: 'erfinv_cuda' not implemented for 'BFloat16'" when I try to fine-tune based on the SliME-Vicuna-7B weight. Could you please provide some suggestions?
**My …
-
i want use video-llava framework use mixtral-7Bx8 的大模型进行训练
改造完成后存在如下问题：
1. 现存不足。。使用h800的现存，跑 vedio-llava on mixtral 7bx8的模型, 报错：显存不足。。
那是因为mixtral 7Bx8 有大约46B 参数，而vicnue 7B只有 7B参数。。 那么我该怎么解…
-
Dear Google AI Team,
I wish to express my strong interest in seeing Google Gemini Flash released to the open-source community.
As a developer and AI enthusiast, I have been incredibly impressed wi…
-
The NCCL timed out while using the zero3 model. How can I solve this problem?
I inherited the large model Mixtral 7BX8 and utilized the Llama architecture, augmenting it with multi-modal capa…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
I am trying to use the built-in capabilities of llamaindex to evaluate the correctness o…
-
### Describe the issue
transformers no longer has SharedDDPOption after v4.35.0
-
### Your current environment
```text
Collecting environment information...
WARNING 10-07 03:01:24 _core_ext.py:180] Failed to import from vllm._core_C with ImportError('libtorch_cuda.so: cannot ope…