-
I am using Gemma-2B and it is not saving checkpoints at all. It hangs (no error, just waiting forever). I use 4 gpus, but even if memory usage is very low (5 GBs out of 24 GBs available, per each gpu)…
-
I am unable to reproduce the performance of llama3 and gemma2 implemented by Keras Hub on the GSM8k benchmark.
paper ref https://arxiv.org/pdf/[2407.21783](https://arxiv.org/pdf/2407.21783) and http…
-
@danielhanchen Hi Daniel, thanks for your work!
having an error just like in the issue #275, but this time while trying to save tuned version of unsloth/gemma-2-9b-it-bnb-4bit.
>> model.save_p…
-
When using model_worker with transformers to run Gemma 2 9B model does not work correctly and the conversation template applied to Gemma 2 model continue to generate response until model_worker is kil…
-
### Describe the bug
Not sure if this is a widespread issue, but as @osanseviero reported, sharing in https://huggingface.co/spaces/gokaygokay/Gemma-2-llamacpp is broken.
> I tried https://hugging…
-
Hi. Raising this issue as I am experimenting a much slower inference time with Gemma-1 models.
> Environment:
> - xformers 0.0.26.post1 pypi_0 pypi
> - unsloth …
-
Hello again,
I am trying to generate the required files from generate-ds and train-supervised.
When I execute generate-ds coqa related files are not getting generated and with train-supervised I a…
-
# Problem
I have encountered many issues with the wrong model default settings (incorrect prompt template, the stop words missing, etc.).
e.g., comments in Jan 0.5.7 Release Sign Off janhq/jan#3818…
-
```python
from edsl import Model
import time
models_list = [['Austism/chronos-hermes-13b-v2', 'deep_infra', 0], ['BAAI/bge-base-en-v1.5', 'together', 1], ['BAAI/bge-large-en-v1.5', 'together', …
-
I have been experimenting with different models in fllama, specifically Gemma, Phi3, and QWEN 2. I noticed significant differences in the performance and response quality across these models:
Gemma…