-
Hi neuralmagic team !
Very nice work with AutoFP8 ! We were thinking of integrating AutoFP8 in transformers, so that users can run your checkpoints directly with transformers ! We would simply rep…
-
Is it possible to use the `musicgen-melody model` in the [Transformers library](https://github.com/huggingface/transformers) like the [`musicgen-small model`](https://github.com/facebookresearch/audio…
-
### Describe the issue
we currently use large max_length in beam search, but we got max_length
-
## Description
The [hugging-face](https://rubygems.org/gems/hugging-face/versions/0.1.0?locale=en) gem only allows us to call the huggingface.co Inference API and we're unable to pull down models lo…
-
Here is the Error Log when i run the code in Mobaxterm.
2024-11-05 19:59:58.279712: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to regi…
-
### Anything you want to discuss about vllm.
Got error
---
ValueError: The checkpoint you are trying to load has model type `cohere` but Transformers does not recognize this architecture. This coul…
-
Hi,
Can you please add a requirements.txt file for easier reproducibility?
Thanks
-
## Issue encountered
It would be good to have a system for evaluating both the relevance of the RAG and its use by the LLM in producing the response. My first intuition would be a multi-stage system …
-
### Feature request
Model2vec would make for a great addition to transformers.js:
https://github.com/MinishLab/model2vec
### Motivation
The library distills conventional embedding models and prod…
do-me updated
2 weeks ago
-
Hi TensorRT-LLM team, Your work is incredible.
By following the READme file for [multi-modeling](https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/multimodal/README.md), we were sucess to run…