-
### Model description
Hi dear:
Thanks for your source code. can support for colbertv2.0 deployment ?
Thank you!
### Open source status
- [ ] The model implementation is available on transformer…
-
Hi,
I am encountering an issue when running inference on the Llama-3-VILA1.5-8B model. The error message I receive is:
```RuntimeError: FlashAttention only supports Ampere GPUs or newer.```
I…
-
Currently, `streamly` does not provide `MonadPlus` instances for its transformers. (#18, #20, #60)
However, there is a well-known pattern for implementing library-agnostic stream sources (http://ww…
-
Great job! Would it be possible to upstream your transformer changes (or at least provide a diff of the changes)? Long term it isn't sustainable to run off of a transformers fork. If you could provide…
-
It would be interesting to be able to use `loom` with open source LLMs such as GPT-Neo-X, FLAN-UL2, and LLaMA. The [transformers](https://github.com/huggingface/transformers) library by Huggingface h…
-
When using the whispering-tigeri-ui.exe and selecting the text-translation type: Seamless M4T with the following settings:
CUDA
Large
float 16 precision
English to Chinese
The following error o…
-
python export_qwen2_1.5.py -m /media/yanxiao/机械硬盘1/LLM/Qwen2-7B-Instruct -o ./
WARNING:root:*** Note: please apply modications to model before conversion:
modication 1: in Qwen2ForCausalLM.forwar…
-
When I try to run the default-rocm docker images it fails with the issue below, i believe i set up docker compose correctly
```
text-generation-webui | RuntimeError: Failed to import transformers.g…
-
我运行的程序：
import paddlehub as hub
module = hub.Module(name="stable_diffusion")
results = module.generate_image(text_prompts=["原神中的派蒙"], style="油画")
每次都会出现的警告：
/usr/bin/python3 /Users/wisers/Pycha…
-
**Is your feature request related to a problem? Please describe.**
Currently, if `torch_dtype` is not specified, the pipeline defaults to loading in `float32`. This behavior causes `float16` or `bflo…