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.q5_K_M.bin from TheBloke/EverythingLM-13B-16K-GGML: direct link, hf CLI and curl.
- Browser
- Download file 9.23 GB
-
https://huggingface.co/TheBloke/EverythingLM-13B-16K-GGML/resolve/main/everythinglm-13b-16k.ggmlv3.q5_K_M.bin
- Command line
-
hf download hf://TheBloke/EverythingLM-13B-16K-GGML/everythinglm-13b-16k.ggmlv3.q5_K_M.bin
-
curl -L -o everythinglm-13b-16k.ggmlv3.q5_K_M.bin https://huggingface.co/TheBloke/EverythingLM-13B-16K-GGML/resolve/main/everythinglm-13b-16k.ggmlv3.q5_K_M.bin
9.23 GB
- Xet hash:
- 5e731d5b645dc80351a46867cd00ffec2917a15d863409a7c3297e1f080672eb
- Size of remote file:
- 9.23 GB
- SHA256:
- f61f4bdbcc7ee970fef7321011ffe1853fe23ed588435c22fb8d68213ee7a716
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.