Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,25 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
2 |
tags:
|
|
|
3 |
- w4a16
|
4 |
- int4
|
5 |
- vllm
|
|
|
|
|
6 |
license: apache-2.0
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
|
|
|
|
|
|
12 |
---
|
13 |
<h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
|
14 |
granite-3.1-8b-instruct-quantized.w4a16
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
base_model:
|
5 |
+
- ibm-granite/granite-3.1-8b-instruct
|
6 |
+
pipeline_tag: text-generation
|
7 |
tags:
|
8 |
+
- granite
|
9 |
- w4a16
|
10 |
- int4
|
11 |
- vllm
|
12 |
+
- conversational
|
13 |
+
- compressed-tensors
|
14 |
license: apache-2.0
|
15 |
+
license_name: apache-2.0
|
16 |
+
name: RedHatAI/granite-3.1-8b-instruct-quantized.w4a16
|
17 |
+
description: This model was obtained by quantizing the weights of ibm-granite/granite-3.1-8b-instruct to INT4 data type.
|
18 |
+
readme: https://huggingface.co/RedHatAI/granite-3.1-8b-instruct-quantized.w4a16/main/README.md
|
19 |
+
tasks:
|
20 |
+
- text-to-text
|
21 |
+
provider: IBM
|
22 |
+
license_link: https://www.apache.org/licenses/LICENSE-2.0
|
23 |
---
|
24 |
<h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
|
25 |
granite-3.1-8b-instruct-quantized.w4a16
|