jacobfulano
commited on
Commit
•
9580a8e
1
Parent(s):
8b737ec
Update README.md
Browse files
README.md
CHANGED
@@ -35,21 +35,21 @@ Apache-2.0 (commercial use permitted)
|
|
35 |
### Example Dialogue
|
36 |
|
37 |
**SamIAm85**:
|
38 |
-
I want you to come up with a tweet based on this summary of the article:
|
39 |
|
40 |
-
"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.
|
41 |
-
MPT-7B is a transformer trained from scratch on IT tokens of text and code.
|
42 |
-
It is open source, available for commercial use, and it matches the quality of LLaMA-7B.
|
43 |
-
MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.
|
44 |
-
Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.
|
45 |
-
For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!
|
46 |
|
47 |
**MPT-7B-Instruct**:
|
48 |
>Here's my suggestion for a tweet:
|
49 |
>"Exciting news! @MosaicML has launched #MPT_7B - a new standard for open-source, commercially usable LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: https://bit.ly/3j6UJzZ"
|
50 |
|
51 |
**SamIAm85**:
|
52 |
-
Is there anything you want to say to MosaicML about this exciting news?
|
53 |
|
54 |
**MPT-7B-Instruct**:
|
55 |
> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.
|
|
|
35 |
### Example Dialogue
|
36 |
|
37 |
**SamIAm85**:
|
38 |
+
>I want you to come up with a tweet based on this summary of the article:
|
39 |
|
40 |
+
>"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.
|
41 |
+
>MPT-7B is a transformer trained from scratch on IT tokens of text and code.
|
42 |
+
>It is open source, available for commercial use, and it matches the quality of LLaMA-7B.
|
43 |
+
>MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.
|
44 |
+
>Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.
|
45 |
+
>For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!
|
46 |
|
47 |
**MPT-7B-Instruct**:
|
48 |
>Here's my suggestion for a tweet:
|
49 |
>"Exciting news! @MosaicML has launched #MPT_7B - a new standard for open-source, commercially usable LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: https://bit.ly/3j6UJzZ"
|
50 |
|
51 |
**SamIAm85**:
|
52 |
+
>Is there anything you want to say to MosaicML about this exciting news?
|
53 |
|
54 |
**MPT-7B-Instruct**:
|
55 |
> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.
|