-
**Describe the bug**
Hello, I'm attempting to build the nightly version for aarch64 Linux with CUDA enabled, but I encounter the following error:
```
In file included from /mnt/ssd_drive/repos/onnxru…
-
Hi,
I already found #279 and I think I have the same issue.
I am using the code from #279 for benchmarking (only checking faster-whisper).
A 2 seconds wav-file needs nearly 3 seconds to process w…
-
Extend and improve the Beam feature of Big-AGI.
Possible vectors for improvement are below:
- **UX**:
- [ ] Respond to single chats (chat bubble in the bottom-left) #553
- [ ] Looping Beam (…
-
Env: torch2.4 cuda 12.4 unsloth main
below is the code errored
```
from unsloth import FastLanguageModel
import torch
model_id="unsloth/gemma-2-2b-it-bnb-4bit"
model, tokenizer = FastLanguageM…
-
This only happens with `BEAM=1`. `BEAM=0`, `BEAM=2`, `BEAM=3` all work fine
This happens because exo runs tinygrad inference on another thread.
Example command to reproduce: `DEBUG=6 BEAM=1 python3 …
-
Hi!
Thanks for open-sourcing the codes for Beam Retrieval.
Do you have any plans to share the checkpoints of the models?
Thanks a lot!
-
### Describe the feature request
Currently there is support for beam search for T5 model. But the 3 models (encoder, decoder, decoder_with_past) or 2 models (encoder_decoder_init, decoder) would be j…
-
### System Info
nightly build transformers version
### Who can help?
@ArthurZucker
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] An officiall…
Mirmu updated
7 months ago
-
Hi there,
I have inherited a sunny beam that works on 868Mhz.
The display is blank, and it appears someone has been inside it and broken the ribbon cable to the display, so it's hard to know if it i…
-
**Why**
Users can select temperature, top-p for the models while beaming responses. This would allow them to compare responses from the same model but with different parameters and test which paramet…