Add recommendations for use
Browse files
README.md
CHANGED
@@ -13,6 +13,8 @@ license: apache-2.0
|
|
13 |
|
14 |
*Paper coming soon π.*
|
15 |
|
|
|
|
|
16 |
## Why use Falcon-7B-Instruct?
|
17 |
|
18 |
* **You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).**
|
@@ -54,6 +56,10 @@ for seq in sequences:
|
|
54 |
|
55 |
π₯ **Falcon LLMs require PyTorch 2.0 for use with `transformers`!**
|
56 |
|
|
|
|
|
|
|
|
|
57 |
|
58 |
# Model Card for Falcon-7B-Instruct
|
59 |
|
|
|
13 |
|
14 |
*Paper coming soon π.*
|
15 |
|
16 |
+
π€ To get started with Falcon (inference, finetuning, quantization, etc.), we recommend reading [this great blogpost fron HF](https://huggingface.co/blog/falcon)!
|
17 |
+
|
18 |
## Why use Falcon-7B-Instruct?
|
19 |
|
20 |
* **You are looking for a ready-to-use chat/instruct model based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b).**
|
|
|
56 |
|
57 |
π₯ **Falcon LLMs require PyTorch 2.0 for use with `transformers`!**
|
58 |
|
59 |
+
For fast inference with Falcon, check-out [Text Generation Inference](https://github.com/huggingface/text-generation-inference)! Read more in this [blogpost]((https://huggingface.co/blog/falcon).
|
60 |
+
|
61 |
+
You will need **at least 16GB of memory** to swiftly run inference with Falcon-7B-Instruct.
|
62 |
+
|
63 |
|
64 |
# Model Card for Falcon-7B-Instruct
|
65 |
|