-
**Describe the bug**
Hi, I tried to finetune gemma-2b model with sharding_array=(1, 1, 1, -1) on Kaggle tpu vm v3-8.
there are two parameters about batch size in TrainArguments: total_batch_size, …
-
When doing inference on Gemma-2-2B with Flash Attention 2, I get the following error. It works just fine with Flash Attention disabled.
transformers==4.44.0
torch==2.4.0
flash-attn==2.6.3
python…
-
* Gemma 7B produces gibberish output
* 2B seem to be working well though
-
Minor issue, but piping to stdin doesn't work on windows with git bash
```
$ cat README.md | ollama run gemma "What is in this document?"
failed to get console mode for stdin: The handle is inva…
-
cuda 12.1
autoawq-0.2.3+cu121
File "/root/anaconda3/envs/auto_awq/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File…
-
**目标**
> 本提议所希望看到的改动的目标是什么？
> 这些改动能带来什么价值？
**实施方案**
> 详细提供该系统改进的实施方案
- https://huggingface.co/google/gemma-7b-it
- Gemma 加入到推理的管线上 https://blog.google/technology/developers/gemma-open-mode…
-
Hi there,When I load the model by fastchat or ollama there was the unrecognizable characters back to me, here is the example
```
### Instructions:
Your task is to convert a question into a SQL quer…
-
GPU info:
```
QUALCOMM build : 7b26bdd942, Iab69c31769
Build Date : 08/28…
-
**Bug description**
I encountered an error when using MetaGPT to call the local ollama, and it failed to function. However, directly invoking ollama using Python works fine.
**Environment inform…
-
# Bug Report
## Installation Method
Docker Windows
## Environment
- **Open WebUI Version:** 0.3.21
- **Ollama (if applicable):** 3.10
- **Operating System:** IOS
- **Browser (if appli…