CalamitousFelicitousness
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,7 @@ tags:
|
|
9 |
- multimodal
|
10 |
base_model: Qwen/Qwen2-VL-72B-Instruct
|
11 |
---
|
|
|
12 |
|
13 |
# Qwen2-VL-72B-Instruct-GPTQ-Int8
|
14 |
|
|
|
9 |
- multimodal
|
10 |
base_model: Qwen/Qwen2-VL-72B-Instruct
|
11 |
---
|
12 |
+
# This repo contains a fix for intermediate_size which was incompatible with VLLM parallel inference. This repo will allow you to run with tensor_parallel of 2.
|
13 |
|
14 |
# Qwen2-VL-72B-Instruct-GPTQ-Int8
|
15 |
|