Instructions to use TheBloke/falcon-40b-instruct-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/falcon-40b-instruct-GGML with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/falcon-40b-instruct-GGML", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
d40197d
-
Update README.md
8a940c6 -
Update README.md
283562e -
Update README.md
52df286 -
Commit new GGCC format files
b506f71 -
Delete falcon40b-instruct.ggmlv3.q8_0.bin
4acace0 -
Delete falcon40b-instruct.ggmlv3.q6_K.bin
c6b36c8 -
Delete falcon40b-instruct.ggmlv3.q5_K_S.bin
0536882 -
Delete falcon40b-instruct.ggmlv3.q4_K_S.bin
7b8afd5 -
Delete falcon40b-instruct.ggmlv3.q3_K_S.bin
9b3a81c -
Delete falcon40b-instruct.ggmlv3.q2_K.bin
1010520
-
Update README.md
ef68241 -
Update README.md
b93b1bf -
Add config.json for ctransformers
2ba684d
-
Update README.md
bd282c1 -
Update README.md
b58cc00 -
Delete falcon40b-instruct.ggmlv3.q5_K_M.bin
801a3be -
Delete falcon40b-instruct.ggmlv3.q4_K_M.bin
3997033 -
Delete falcon40b-instruct.ggmlv3.q3_K_M.bin
2d272de -
Delete falcon40b-instruct.ggmlv3.q3_K_L.bin
c131903
-
Update README.md
4b2981d -
Update README.md
d11efd9 -
Update README.md
303874e -
Update README.md
3704f5b -
Initial GGML model commit
9cbcab1 -
Update README.md
b658e12 -
Add new GGMLv3 k-quant Falcon40B GGMLs
7def927 -
Delete Falcon-40b-Instruct.ggmlv3.q5_1.bin
d6c8295 -
Delete Falcon-40b-Instruct.ggmlv3.q5_0.bin
07f900c -
Delete Falcon-40b-Instruct.ggmlv3.q4_1.bin
101a337 -
Delete Falcon-40b-Instruct.ggmlv3.q4_0.bin
c84036d
-
Update README.md
d3cee1e -
Update README.md
5920eb5 -
Update README.md
946dfe9 -
Update README.md
92baea4 -
Update README.md
998b90c -
Update README.md
27cf5ed -
Initial GGML model commit
40290f3 -
Initial GGML model commit.
9111cd3
-
initial commit
25ea3d0