doberst commited on
Commit
1fd779b
1 Parent(s): 87b50de

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -3,17 +3,16 @@ license: llama3.2
3
  inference: false
4
  tags:
5
  - green
6
- - p1
7
  - llmware-chat
8
  - ov
9
- - emerald
10
  ---
11
 
12
- # llama-3.2-1b-instruct-onnx
13
 
14
- **llama-3.2-1b-instruct-onnx** is an ONNX int4 quantized version of Llama 3.2 1B Instruct, providing a very small, very fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
15
 
16
- [**llama-3.2-1b-instruct**](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) is a new 1B chat foundation model from Meta.
17
 
18
 
19
  ### Model Description
@@ -21,7 +20,7 @@ tags:
21
  - **Developed by:** meta-llama
22
  - **Quantized by:** llmware
23
  - **Model type:** llama-3.2
24
- - **Parameters:** 1 billion
25
  - **Model Parent:** meta-llama/Meta-Llama-3.2-1B-Instruct
26
  - **Language(s) (NLP):** English
27
  - **License:** Llama 3.2 Community License
 
3
  inference: false
4
  tags:
5
  - green
6
+ - p3
7
  - llmware-chat
8
  - ov
 
9
  ---
10
 
11
+ # llama-3.2-3b-instruct-onnx
12
 
13
+ **llama-3.2-3b-instruct-onnx** is an ONNX int4 quantized version of Llama 3.2 3B Instruct, providing a very small, very fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
14
 
15
+ [**llama-3.2-3b-instruct**](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) is a new 3B chat foundation model from Meta.
16
 
17
 
18
  ### Model Description
 
20
  - **Developed by:** meta-llama
21
  - **Quantized by:** llmware
22
  - **Model type:** llama-3.2
23
+ - **Parameters:** 3 billion
24
  - **Model Parent:** meta-llama/Meta-Llama-3.2-1B-Instruct
25
  - **Language(s) (NLP):** English
26
  - **License:** Llama 3.2 Community License