-
### Class | 类型
None
### Feature Request | 功能请求
# chatglm3已经更新:
https://github.com/THUDM/ChatGLM3
更强大的基础模型: ChatGLM3-6B 的基础模型 ChatGLM3-6B-Base 采用了更多样的训练数据、更充分的训练步数和更合理的训练策略。在语义、数学、推理、代码、知识等不同角度的数据…
-
Run vllm serving test on ARC with below issue:
NFO 07-04 19:10:08 async_llm_engine.py:152] Aborted request cmpl-e5fb5cad96e9402dabbbece3611ae22f-0.
INFO: 127.0.0.1:41772 - "POST /v1/completions …
-
benchmark chatglm3-6b on Arc A770 with 1k input and 512 output, the performance is as below:
![image](https://github.com/intel-analytics/BigDL/assets/99886928/72d0312a-5651-46c6-86f0-576b0931f451)
-
### System Info
- CPU: INTEL RPL
- GPU Name: NVIDIA GTX 3090
- TensorRT-LLM: tensorrt_llm==0.11.0.dev2024060400
- Container Used: Yes and reproduced in Conda as well
- Driver Version: 555.42.02
…
-
老哥我想问下你用gemma来 all-linere lora微调用了多少显存,我用qwen1.5-7b和chatglm3-6b来调全都oom了,你那边有训练设备、时间相关的信息吗?感谢
-
### System Info
```shell
Optimum Version: 1.18.0
Python Version: 3.8
Platform: Windows, x86_64
```
### Who can help?
@michaelbenayoun @JingyaHuang @echarlaix
I am writing to report an issue I e…
-
如题,
-
OS: Win10 22H2 19045.3803
Python=3.9 and install the env according to https://bigdl.readthedocs.io/en/latest/doc/LLM/Overview/install_gpu.html
Test code:
```python
import time
from bigdl.llm.tr…
-
### 🚀 The feature, motivation and pitch
This project is very nice! Chatglm2-6b and chatglm3-6b work well in this project. But could you restore support for chatglm-6b? It's a very popular model.
###…
-
### System Info / 系統信息
>>> print(torch.__version__)
2.3.1+cu121
>>> print(torch.version.cuda)
12.1
>>> print(torch.backends.cudnn.version())
8902
>>> print(transformers.__version__)
4.43.2
>…