CrispStrobe
CrispStrobe
Using ollama 0.1.25 under Windows, sometimes my GPU (A1000) is detected: From server.log: time=2024-02-21T17:04:44.912+01:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2" time=2024-02-21T17:04:44.912+01:00 level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 8.6" time=2024-02-21T17:04:44.912+01:00 level=DEBUG source=gpu.go:251...
thanks for building this. looks nice on quick first try. but for some models, you might want to check the prompt template / stop parameters / parse yaml template files...
... because seemingly template not found anymore. you can use image_name="winglian/axolotl-runpod:main-latest", without #template_id="eul6o46pab", but then get in the container: ... ServerApp] Bad config encountered during initialization: /workspace is outside root...
... would need vocab_type bpe, see here for illustration https://colab.research.google.com/drive/1q1hTxLZOCRf9n0KdxSSu3tD0EI5QufrV?usp=sharing (i also made a few adaptions for faster running for my use case) thank you and keep up the great...
### Prerequisites - [X] I am running the latest code. Mention the version if possible as well. - [X] I carefully followed the [README.md](https://github.com/Mozilla-Ocho/llamafile/blob/master/README.md). - [x] I searched using keywords...
thanks for providing this toolset. i am unsure how utils.extend_model_vocab is intended to be used. in current form, it takes checkpoints only. when i try to adapt it to extend...
i seemingly cannot generate ELFs anymore per those URL tricks. but it works still in makecode arcade beta per choosing rpi0 as hardware and downloading the file.
the transcribe.py that gets installed by pip install differs largely from the one in the current repo. especially, BatchedInferencePipeline is not present there. so one has to git clone &...
... did not work for me right now, whereas previously it did. Cannot check this further at the moment, but maybe you might want to. Environment was kaggle and colab,...