Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
<div style="width: auto; margin-left: auto; margin-right: auto; background-color:black">
|
| 5 |
<img src="https://assets-global.website-files.com/6423879a8f63c1bb18d74bfa/648818d56d04c3bdf36d71ab_Refuel_rev8-01_ts-p-1600.png" alt="Refuel.ai" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
|
@@ -7,28 +12,24 @@ license: cc-by-nc-4.0
|
|
| 7 |
|
| 8 |
## Model Details
|
| 9 |
|
| 10 |
-
RefuelLLM-2-small, aka Llama-3-Refueled, is a Llama3-8B base model
|
| 11 |
-
|
| 12 |
* More details about [RefuelLLM-2 family of models](https://www.refuel.ai/blog-posts/announcing-refuel-llm-2)
|
| 13 |
* You can also try out the models in Refuel's [LLM playground](https://labs.refuel.ai/playground)
|
| 14 |
|
| 15 |
-
**Model developers** Refuel AI
|
| 16 |
|
| 17 |
-
**Input**
|
| 18 |
|
| 19 |
-
**Output**
|
| 20 |
|
| 21 |
-
**
|
| 22 |
|
| 23 |
-
**
|
| 24 |
|
| 25 |
## How to use
|
| 26 |
|
| 27 |
-
This repository contains weights for RefuelLLM-2-small that are compatible for use with HuggingFace.
|
| 28 |
-
|
| 29 |
-
### Use with transformers
|
| 30 |
-
|
| 31 |
-
See the snippet below for usage with Transformers:
|
| 32 |
|
| 33 |
```python
|
| 34 |
>>> import torch
|
|
@@ -78,4 +79,4 @@ In this section, we report the results for Refuel models on our benchmark of lab
|
|
| 78 |
## Limitations
|
| 79 |
|
| 80 |
The RefuelLLM-v2-small does not have any moderation mechanisms. We're looking forward to engaging with the community
|
| 81 |
-
on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- data labeling
|
| 8 |
---
|
| 9 |
<div style="width: auto; margin-left: auto; margin-right: auto; background-color:black">
|
| 10 |
<img src="https://assets-global.website-files.com/6423879a8f63c1bb18d74bfa/648818d56d04c3bdf36d71ab_Refuel_rev8-01_ts-p-1600.png" alt="Refuel.ai" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
|
|
|
| 12 |
|
| 13 |
## Model Details
|
| 14 |
|
| 15 |
+
RefuelLLM-2-small, aka Llama-3-Refueled, is a Llama3-8B base model instruction tuned on a corpus of 2750+ datasets, spanning tasks such as classification, reading comprehension, structured attribute extraction and entity resolution. We're excited to open-source the model for the community to build on top of.
|
| 16 |
+
|
| 17 |
* More details about [RefuelLLM-2 family of models](https://www.refuel.ai/blog-posts/announcing-refuel-llm-2)
|
| 18 |
* You can also try out the models in Refuel's [LLM playground](https://labs.refuel.ai/playground)
|
| 19 |
|
| 20 |
+
**Model developers** - Refuel AI
|
| 21 |
|
| 22 |
+
**Input** - Text only.
|
| 23 |
|
| 24 |
+
**Output** - Text only.
|
| 25 |
|
| 26 |
+
**Architecture** - RefuelLLM-2-small is built on top of Llama-3-8B-instruct which is an auto-regressive language model that uses an optimized transformer architecture.
|
| 27 |
|
| 28 |
+
**Release Date** - May 8, 2024.
|
| 29 |
|
| 30 |
## How to use
|
| 31 |
|
| 32 |
+
This repository contains weights for RefuelLLM-2-small that are compatible for use with HuggingFace. See the snippet below for usage with Transformers:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
```python
|
| 35 |
>>> import torch
|
|
|
|
| 79 |
## Limitations
|
| 80 |
|
| 81 |
The RefuelLLM-v2-small does not have any moderation mechanisms. We're looking forward to engaging with the community
|
| 82 |
+
on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
|