Text Generation
ELM
English
dev-slx commited on
Commit
3f338f6
1 Parent(s): 618a701

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -14
README.md CHANGED
@@ -1,14 +1,12 @@
1
  # SliceX AI™ ELM (Efficient Language Models)
2
  This repository contains code to run our ELM models.
3
 
4
- Models are located in the "models" folder. ELM models in this repository comes in three sizes (elm-1.0, elm-0.75 and elm-0.25) and supports the following use-cases.
5
- - news_classification
6
- - toxicity_detection
7
  - news_content_generation
8
 
9
  ## Download ELM repo
10
  ```bash
11
- git clone [email protected]:slicexai/elm-0.25-v0.1
12
  sudo apt-get intall git-lfs
13
  git lfs install
14
  ```
@@ -20,11 +18,11 @@ PATH=$PATH:/<absolute-path>/git-lfs-3.2.0/
20
  git lfs install
21
  ```
22
 
23
- ## Download ELM task-specific model checkpoints
24
  ```bash
25
- cd elm-0.25-v0.1
26
- git lfs pull -I models/elm-0.25_news_classification/ckpt.pt
27
- git lfs pull -I models/elm-0.25_toxicity_detection/ckpt.pt
28
  git lfs pull -I models/elm-0.25_news_content_generation/ckpt.pt
29
  ```
30
 
@@ -36,13 +34,13 @@ pip install -r requirements.txt
36
  ## How to use - Run ELM on a sample task (e.g., news classification)
37
  ```bash
38
  python run.py <elm-model-directory>
39
- E.g. python run.py models/elm-0.25_news_classification
40
  ```
41
- Prompts for the specific tasks can be found in the corresponding checkpoint directory. See an example below in the form of `models/elm-0.25_news_classification/example_prompts.json`.
42
  ```json
43
  {
44
- "inputs": ["GM May Close Plant in Europe DETROIT (Reuters) - General Motors Corp. &lt;A HREF=\"http://www.investor.reuters.com/FullQuote.aspx?ticker=GM.N target=/stocks/quickinfo/fullquote\"&gt;GM.N&lt;/A&gt; will likely cut some jobs in Europe and may close a plant there as part of a restructuring plan under development to try to return the region to profitability, the U.S. automaker said on Wednesday."],
45
- "template": "[INST]Below is a news article. Please classify it under one of the following classes (World, Business, Sports, Sci/Tech). Please format your response as a JSON payload.\n\n### Article: {input}\n\n### JSON Response:[/INST]"
46
  }
47
  ```
48
 
@@ -50,7 +48,7 @@ Running the above command returns the following response
50
 
51
  ```json
52
  {
53
- "prompt": "[INST]Below is a news article. Please classify it under one of the following classes (World, Business, Sports, Sci/Tech). Please format your response as a JSON payload.\n\n### Article: GM May Close Plant in Europe DETROIT (Reuters) - General Motors Corp. &lt;A HREF=\"http://www.investor.reuters.com/FullQuote.aspx?ticker=GM.N target=/stocks/quickinfo/fullquote\"&gt;GM.N&lt;/A&gt; will likely cut some jobs in Europe and may close a plant there as part of a restructuring plan under development to try to return the region to profitability, the U.S. automaker said on Wednesday.\n\n### JSON Response:[/INST]",
54
- "response": "{'text_label': 'Business'}"
55
  }
56
  ```
 
1
  # SliceX AI™ ELM (Efficient Language Models)
2
  This repository contains code to run our ELM models.
3
 
4
+ Models are located in the "models" folder. ELM models in this repository comes in three sizes (elm-1.0, elm-0.75 and elm-0.25) and supports the following use-case.
 
 
5
  - news_content_generation
6
 
7
  ## Download ELM repo
8
  ```bash
9
+ git clone [email protected]:slicexai/elm-v0.1_news_content_generation
10
  sudo apt-get intall git-lfs
11
  git lfs install
12
  ```
 
18
  git lfs install
19
  ```
20
 
21
+ ## Download ELM model checkpoints
22
  ```bash
23
+ cd elm-v0.1_news_content_generation
24
+ git lfs pull -I models/elm-1.0_news_content_generation/ckpt.pt
25
+ git lfs pull -I models/elm-0.75_news_content_generation/ckpt.pt
26
  git lfs pull -I models/elm-0.25_news_content_generation/ckpt.pt
27
  ```
28
 
 
34
  ## How to use - Run ELM on a sample task (e.g., news classification)
35
  ```bash
36
  python run.py <elm-model-directory>
37
+ E.g. python run.py models/elm-0.75_news_content_generation
38
  ```
39
+ Prompts for the specific tasks can be found in the corresponding checkpoint directory. See an example below in the form of `models/elm-0.75_news_content_generation/example_prompts.json`.
40
  ```json
41
  {
42
+ "inputs": ["Scientists Invent 'Invisible' Metamaterial With Bonus Reflect Mode"],
43
+ "template": "[INST]The following headline is the headline of a news report. Please write the content of the news passage based on only this headline.\n\nHeadline: {input} \n\nContent:[/INST]"
44
  }
45
  ```
46
 
 
48
 
49
  ```json
50
  {
51
+ "prompt": "[INST]The following headline is the headline of a news report. Please write the content of the news passage based on only this headline.\n\nHeadline: Scientists Invent 'Invisible' Metamaterial With Bonus Reflect Mode \n\nContent:[/INST]",
52
+ "response": "A team of scientists have created an invisible material that can make objects disappear. It is made of a special material that creates a layer of nanoscale dots that allow light to enter from the material, directing it to a layer of gas that allows light to enter from the material. The material is able to levitate and roll off its surface without leaving the material. This technology could have many future applications in battery technology, microelectronics, and more. A video demonstrating the material is available in the article."
53
  }
54
  ```