Commit
•
348b81d
1
Parent(s):
bc7a41c
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,14 +12,17 @@ We have a [live interactive demo](https://huggingface.co/spaces/joaogante/transf
|
|
| 12 |
We are also benchmarking many instruction-tuned models at [declare-lab/flan-eval](https://github.com/declare-lab/flan-eval).
|
| 13 |
Our pretrained models are fully available on HuggingFace 🤗 :
|
| 14 |
|
| 15 |
-
| Model
|
| 16 |
-
|
| 17 |
-
| [Flan-Alpaca-Base](https://huggingface.co/declare-lab/flan-alpaca-base)
|
| 18 |
-
| [Flan-Alpaca-Large](https://huggingface.co/declare-lab/flan-alpaca-large)
|
| 19 |
-
| [Flan-Alpaca-XL](https://huggingface.co/declare-lab/flan-alpaca-xl)
|
| 20 |
-
| [Flan-Alpaca-XXL](https://huggingface.co/declare-lab/flan-alpaca-xxl)
|
| 21 |
-
| [Flan-GPT4All-XL](https://huggingface.co/declare-lab/flan-gpt4all-xl)
|
| 22 |
-
| [Flan-ShareGPT-XL](https://huggingface.co/declare-lab/flan-sharegpt-xl)
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
### Why?
|
| 25 |
|
|
@@ -39,7 +42,7 @@ less diverse) instructions such as [Flan-T5](https://arxiv.org/abs/2210.11416).
|
|
| 39 |
from transformers import pipeline
|
| 40 |
|
| 41 |
prompt = "Write an email about an alpaca that likes flan"
|
| 42 |
-
model = pipeline(model="declare-lab/flan-alpaca-xl")
|
| 43 |
model(prompt, max_length=128, do_sample=True)
|
| 44 |
|
| 45 |
# Dear AlpacaFriend,
|
|
|
|
| 12 |
We are also benchmarking many instruction-tuned models at [declare-lab/flan-eval](https://github.com/declare-lab/flan-eval).
|
| 13 |
Our pretrained models are fully available on HuggingFace 🤗 :
|
| 14 |
|
| 15 |
+
| Model | Parameters | Instruction Data | Training GPUs |
|
| 16 |
+
|----------------------------------------------------------------------------------|------------|----------------------------------------------------------------------------------------------------------------------------------------------------|-----------------|
|
| 17 |
+
| [Flan-Alpaca-Base](https://huggingface.co/declare-lab/flan-alpaca-base) | 220M | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 1x A6000 |
|
| 18 |
+
| [Flan-Alpaca-Large](https://huggingface.co/declare-lab/flan-alpaca-large) | 770M | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 1x A6000 |
|
| 19 |
+
| [Flan-Alpaca-XL](https://huggingface.co/declare-lab/flan-alpaca-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 1x A6000 |
|
| 20 |
+
| [Flan-Alpaca-XXL](https://huggingface.co/declare-lab/flan-alpaca-xxl) | 11B | [Flan](https://github.com/google-research/FLAN), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) | 4x A6000 (FSDP) |
|
| 21 |
+
| [Flan-GPT4All-XL](https://huggingface.co/declare-lab/flan-gpt4all-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [GPT4All](https://github.com/nomic-ai/gpt4all) | 1x A6000 |
|
| 22 |
+
| [Flan-ShareGPT-XL](https://huggingface.co/declare-lab/flan-sharegpt-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [ShareGPT](https://github.com/domeccleston/sharegpt)/[Vicuna](https://github.com/lm-sys/FastChat) | 1x A6000 |
|
| 23 |
+
| [Flan-Alpaca-GPT4-XL*](https://huggingface.co/declare-lab/flan-alpaca-gpt4-xl) | 3B | [Flan](https://github.com/google-research/FLAN), [GPT4-Alpaca](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) | 1x A6000 |
|
| 24 |
+
|
| 25 |
+
*recommended for better performance
|
| 26 |
|
| 27 |
### Why?
|
| 28 |
|
|
|
|
| 42 |
from transformers import pipeline
|
| 43 |
|
| 44 |
prompt = "Write an email about an alpaca that likes flan"
|
| 45 |
+
model = pipeline(model="declare-lab/flan-alpaca-gpt4-xl")
|
| 46 |
model(prompt, max_length=128, do_sample=True)
|
| 47 |
|
| 48 |
# Dear AlpacaFriend,
|