-
### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答？ | Is there an existing ans…
-
**Describe the bug**
What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程，最好有截图)
可以正常启动
CUDA_VISIBLE_DEVICES=0 swift infer --model_type internvl-chat-v1_5-int8 --model_id_or_…
-
Currently when using the default WhisperKit flow of auto downloading models on transcribe, an internet connection is required even if models have already been downloaded in the past due to swift-trans…
-
**Is your feature request related to a problem? Please describe.**
Please consider adding Core ML model package format support to utilize Apple Silicone Nural Engine + GPU.
**Describe the soluti…
-
Context: I'm trying to run the LLMEval iOS application on Apple M1 Pro 32 GB running macOS Version 14.4.1
I've considered the following solutions so far:
1. Ensured I'm running the "Release" bui…
-
**Describe the bug**
尝试使用 swift export 量化导出模型，模型量化执行完成后，程序不保存模型文件且无报错退出
```
(swift) root@autodl-container-36e51198ae-5fff8b56:~# OMP_NUM_THREADS=16 CUDA_VISIBLE_DEVICES=0 swift export \
--ck…
-
**Describe the bug**
首先，我使用4090D*4按照DPO的DEMO训练了自己的数据。执行命令如下：
`# Experimental environment: 4*A100
# Memory usage: 4 * 20G，双卡device_map * 2ddp
nproc_per_node=2
CUDA_VISIBLE_DEVICES=0,1,2,3 \
NPR…
-
https://github.com/modelscope/swift/blob/main/docs/source_en/Multi-Modal/glm4v-best-practice.md
使用的是文档中的命令，eval_acc一直没有变化
# Experimental environment: A100
# 40GB GPU memory
CUDA_VISIBLE_DEVICE…
-
See also #59 and #61
The progress callback on HubApi() no longer works – it is called over and over (unlike #59) but the progress is always 0. In particular the Downloader’s delegate method to obse…
-
**Describe the bug**
We currently support converting a `category` column in `cudf` to a `DictionaryArray` in `pyarrow`:
```python
>>> import cudf
>>> s = cudf.Series([1, 2, 3], dtype='category')…