Hugo Larcher
commited on
Commit
β’
7094fd0
1
Parent(s):
67f33d0
Update README
Browse files
README.md
CHANGED
@@ -7,8 +7,11 @@ inference: false
|
|
7 |
license: apache-2.0
|
8 |
---
|
9 |
|
|
|
10 |
# π Falcon-7B
|
11 |
|
|
|
|
|
12 |
**Falcon-7B is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. It is made available under the Apache 2.0 license.**
|
13 |
|
14 |
*Paper coming soon* π.
|
@@ -233,4 +236,4 @@ To learn more about the pretraining dataset, see the π [RefinedWeb paper](htt
|
|
233 |
Falcon-7B is made available under the Apache 2.0 license.
|
234 |
|
235 |
## Contact
|
236 |
-
falconllm@tii.ae
|
|
|
7 |
license: apache-2.0
|
8 |
---
|
9 |
|
10 |
+
|
11 |
# π Falcon-7B
|
12 |
|
13 |
+
**This is a fix for Falcon-7B to work on Volta architecture (V100s) without FlashAttention. Based on the work of @puru22.**
|
14 |
+
|
15 |
**Falcon-7B is a 7B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. It is made available under the Apache 2.0 license.**
|
16 |
|
17 |
*Paper coming soon* π.
|
|
|
236 |
Falcon-7B is made available under the Apache 2.0 license.
|
237 |
|
238 |
## Contact
|
239 |
+
falconllm@tii.ae
|