-
Hi Daniel,
Thank you so much for releasing such an awesome VLM fine-tuning notebook to the public!
I was really excited, tried the notebook out and found the following error:
![image](https:/…
-
**Is your feature request related to a problem? Please describe.**
ShieldGemma was released in Jul 2024 with [v0.14.3](https://github.com/keras-team/keras-hub/releases/tag/v0.14.3), but since then …
-
I tried some of the `web-ai-demos` on https://chrome.dev/, such as https://chrome.dev/web-ai-demos/perf-client-side-gemma-worker/
Some demos say that the model will take about 30s or 1 minute to lo…
-
### 🚀 The feature, motivation and pitch
Gemma-2 and new Ministral models use alternating sliding window and full attention layers to reduce the size of the KV cache.
The KV cache is a huge inferen…
-
**Describe the bug**
git lfs pull --include gemma-2-9b-it-Q8_0_L.gguf
vs
git lfs pull gemma-2-9b-it-Q8_0_L.gguf (typed accidentally)
does not make it very clear how many files, or how much data …
-
### 🚀 Feature
Similar to EOS token, we should offer an option to add BOS token to the beginning. Might be useful for models like Gemma.
-
Nice project. Open source models are usually good at one task, such as coding, writing, etc. And it would be interesting if we could set a parameter in the .env to specify which model that agent shoul…
-
# Overview
Cosmopediaのプロンプト手法を日本語において実験し、生成速度と生成文の評価を行う。
# Details
[Cosmopedia](https://github.com/huggingface/cosmopedia)のプロンプトを用いて、日本語の高品質合成データを各プロンプトで100サンプル作成し、その品質と速度について評価を行う。生成モデルにはgem…
-
In alle redocs, maar ook bijvoorbeeld hier:
https://vng-realisatie.github.io/gemma-zaken/standaard/zaken/redoc-1.5.1#tag/zaken/operation/zaak_create
![image](https://github.com/VNG-Realisatie/gemm…
-
I am building a container image on top of the official `ollama/ollama` image and I want to store in this image the model I intend to serve, so that I do not have to pull it after startup. The use case…