doberst commited on
Commit
0763f2b
1 Parent(s): ab23c8a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -13
README.md CHANGED
@@ -1,16 +1,20 @@
1
  ---
2
- license: apache-2.0
3
- inference: false
4
- tags: [green, p8, llmware-chat, ov]
 
 
 
 
5
  ---
6
 
7
  # llama-3.1-instruct-ov
8
 
9
  <!-- Provide a quick summary of what the model is/does. -->
10
 
11
- **bling-tiny-llama-ov** is an OpenVino int4 quantized version of BLING Tiny-Llama 1B, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
12
 
13
- [**bling-tiny-llama**](https://huggingface.co/llmware/bling-tiny-llama-v0) is a fact-based question-answering model, optimized for complex business documents.
14
 
15
  Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino)
16
 
@@ -19,14 +23,14 @@ Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmwa
19
 
20
  ### Model Description
21
 
22
- - **Developed by:** llmware
23
- - **Model type:** tinyllama
24
- - **Parameters:** 1.1 billion
25
- - **Model Parent:** llmware/bling-tiny-llama-v0
26
  - **Language(s) (NLP):** English
27
- - **License:** Apache 2.0
28
- - **Uses:** Fact-based question-answering
29
- - **RAG Benchmark Accuracy Score:** 86.5
30
  - **Quantization:** int4
31
 
32
 
@@ -34,4 +38,4 @@ Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmwa
34
 
35
  [llmware on hf](https://www.huggingface.co/llmware)
36
 
37
- [llmware website](https://www.llmware.ai)
 
1
  ---
2
+ license: llama3
3
+ inference: false
4
+ tags:
5
+ - green
6
+ - p8
7
+ - llmware-chat
8
+ - ov
9
  ---
10
 
11
  # llama-3.1-instruct-ov
12
 
13
  <!-- Provide a quick summary of what the model is/does. -->
14
 
15
+ **llama-3.1-instruct-ov-ov** is an OpenVino int4 quantized version of Llama 3.1 Instruct, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
16
 
17
+ [**llama-3.1-instruct**](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) is a leading open source general foundation model from Meta.
18
 
19
  Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino)
20
 
 
23
 
24
  ### Model Description
25
 
26
+ - **Developed by:** meta-llama
27
+ - **Model type:** llama-3.1
28
+ - **Parameters:** 8 billion
29
+ - **Model Parent:** meta-llama/Meta-Llama-3.1-8B-Instruct
30
  - **Language(s) (NLP):** English
31
+ - **License:** Llama 3.1 Community License
32
+ - **Uses:** General chat use cases
33
+ - **RAG Benchmark Accuracy Score:** NA
34
  - **Quantization:** int4
35
 
36
 
 
38
 
39
  [llmware on hf](https://www.huggingface.co/llmware)
40
 
41
+ [llmware website](https://www.llmware.ai)