-
Hi,
I am facing error while retraining.
code
from transformers import Trainer, TrainingArguments
training_args = TrainingArguments(
output_dir="./roberta-retrained",
overwrite_output_…
-
### Your current environment
The output of `python collect_env.py`
```text
环境：
Vllm==0.6.1.post2
torch==2.4.0
Transformers==4.45.1
Accelerate==0.30.1
Tiktoken==0.7.0
startup:
python …
-
Hello, I have replicated the conda environment following [environment.md](https://github.com/IBM/molformer/blob/main/environment.md) and downloaded the pre-trained model checkpoints, when I tried to r…
-
### Checklist
- [ ] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a …
-
I use transformers with a custom script, I see you show how to use this with a custom fast chat script
Do you have boilerplate code on how to wrap a transformers pipeline to use w this?
-
### 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…
-
Hello,
Thank you for developing such an excellent foundation model. When I tried to use Evo's `evo-1-8k-base` model for tokenizer, Evo kept reporting errors about `evo-1-131k-base` (see below). Do yo…
-
When I execute the command `bash scripts/gsm8k/generate.sh`, I used `set_trace` to debug the `_sample_tokens_with_calculator` function. An error occurs when executing the following line:
```
../at…
-
_Imported from https://github.com/dnfield/vector_graphics/issues/250_
Original report by @alefwd on Jul 30, 2024
I have a folder /assets where I have a mix of svgs and json files, and I cannot chang…
-
[https://huggingface.co/upstage/solar-pro-preview-instruct](https://huggingface.co/upstage/solar-pro-preview-instruct)
Solar released a new 22b model, and this thing is crazy powerful. I was just won…