Hugging Face's logo

ethzanalytics
/
RedPajama-INCITE-Chat-3B-v1-GPTQ-4bit-128g

Text Generation
Transformers
gpt_neox
auto-gptq
Model card Files Community
1
pszemraj commited on
Commit
94d2b29
•
1 Parent(s): cd04588

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -3,23 +3,26 @@ license: apache-2.0
3
  inference: false
4
  tags:
5
  - auto-gptq
 
6
  ---
7
 
8
 
9
- # redpajama gptq
10
 
11
  <a href="https://colab.research.google.com/gist/pszemraj/86d2e8485df182302646ed2c5a637059/inference-with-redpajama-incite-chat-3b-v1-gptq-4bit-128g.ipynb">
12
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
13
  </a>
14
 
15
- A GPTQ quantization of the [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1) via auto-gptq.
16
 
17
 
18
  ## Usage
19
 
20
 
21
  > Note that you cannot load directly from the hub with `auto_gptq` yet - if needed you can use [this function](https://gist.github.com/pszemraj/8368cba3400bda6879e521a55d2346d0) to download using the repo name.
22
- install auto-GPTQ
 
 
23
 
24
  ```bash
25
  pip install ninja auto-gptq[triton]
 
3
  inference: false
4
  tags:
5
  - auto-gptq
6
+ pipeline_tag: text-generation
7
  ---
8
 
9
 
10
+ # redpajama gptq: RedPajama-INCITE-Chat-3B-v1
11
 
12
  <a href="https://colab.research.google.com/gist/pszemraj/86d2e8485df182302646ed2c5a637059/inference-with-redpajama-incite-chat-3b-v1-gptq-4bit-128g.ipynb">
13
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
14
  </a>
15
 
16
+ A GPTQ quantization of the [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1) via auto-gptq. Model file is only 2GB.
17
 
18
 
19
  ## Usage
20
 
21
 
22
  > Note that you cannot load directly from the hub with `auto_gptq` yet - if needed you can use [this function](https://gist.github.com/pszemraj/8368cba3400bda6879e521a55d2346d0) to download using the repo name.
23
+
24
+
25
+ first install auto-GPTQ
26
 
27
  ```bash
28
  pip install ninja auto-gptq[triton]