Update README.md
Browse files
README.md
CHANGED
|
@@ -5,10 +5,16 @@ license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4/blob/ma
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
-
base_model: Qwen/Qwen2.5-72B
|
| 9 |
tags:
|
| 10 |
- chat
|
| 11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
# Qwen2.5-72B-Instruct-GPTQ-Int4
|
| 13 |
|
| 14 |
## Introduction
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
+
base_model: Qwen/Qwen2.5-72B
|
| 9 |
tags:
|
| 10 |
- chat
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
---
|
| 14 |
+
## Simple config.json modification of original model to enable 128K context window, necessary as per: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4#processing-long-texts
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
|
| 18 |
# Qwen2.5-72B-Instruct-GPTQ-Int4
|
| 19 |
|
| 20 |
## Introduction
|