-
Hello @tomaarsen , I'm a student who loves using sentence-transformers library.
While looking at the codes, I thought that deduplication could be integrated in CachedGISTEmbedLoss (or just GISTEmbe…
-
### Model Series
Qwen2
### What are the models used?
Qwen2.5-72B-Instruct-GPTQ-Int8 and Qwen2-72B-Instruct-GPTQ-Int8
### What is the scenario where the problem happened?
transformers
### Is this…
-
### What behavior of the library made you think about the improvement?
I need to install torch, transformers, accelerate etc. even if I want to use outlines only with llamacpp backend.
Are these d…
-
### Your current environment
Packages used for both finetuning and inference (vllm==0.3.2):
torch==2.1.2
accelerate==0.27.2
transformers==4.40.1
sentence_transformers==2.7.0
Description:
…
-
你好，是否能想glm4一样提供微调demo？我直接使用glm4的脚本报错，不知道是否是transformers版本的问题，我的transformers是4.44.0，也试过4.43、4.42和4.40分别报不同错误
-
# The Illustrated Image Captioning using transformers - Ankur NLP Enthusiast
The Illustrated Image Captioning using transformers
[https://ankur3107.github.io/blogs/the-illustrated-image-captioning-u…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/axolotl-ai-cloud/axolotl/labels/bug) didn't find any similar reports.
### Exp…
-
We have an output dimension of 768 with the biggest model, but currently we cut at the string length of 3000 -> we should rather go on token size (maybe approx with NLTK tokenizer) on about the dimens…
-
How can we take advantage of https://huggingface.co/docs/transformers/transformers_agents ?
-
### System Info
```Shell
accelerate==1.1.0
```
### Information
- [ ] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] One of the scripts in the examples/ folder of Acce…