Instructions to use TheBloke/EverythingLM-13B-16K-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/EverythingLM-13B-16K-GGML with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/EverythingLM-13B-16K-GGML", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download everythinglm-13b-16k.ggmlv3.q4_K_M.bin from TheBloke/EverythingLM-13B-16K-GGML: direct link, hf CLI and curl.
- Browser
- Download file 7.87 GB
-
https://huggingface.co/TheBloke/EverythingLM-13B-16K-GGML/resolve/main/everythinglm-13b-16k.ggmlv3.q4_K_M.bin
- Command line
-
hf download hf://TheBloke/EverythingLM-13B-16K-GGML/everythinglm-13b-16k.ggmlv3.q4_K_M.bin
-
curl -L -o everythinglm-13b-16k.ggmlv3.q4_K_M.bin https://huggingface.co/TheBloke/EverythingLM-13B-16K-GGML/resolve/main/everythinglm-13b-16k.ggmlv3.q4_K_M.bin
7.87 GB
- Xet hash:
- b55d0590af75e3fe68b26329dfc0c75c1c51786cd0d573f3f5245402be53ce5e
- Size of remote file:
- 7.87 GB
- SHA256:
- 8e5d7e137aa03f56a70faf35d83162eb734917c51b657848a682e3600e76499c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.