Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,10 @@ We introduce LiveCC, the first multimodal LLM with real-time video commentary ca
|
|
| 25 |
> [!Important]
|
| 26 |
> This is the base model, pre-trained on [Live-CC-5M](https://huggingface.co/datasets/chenjoya/Live-CC-5M) dataset only with our proposed streaming frame-words paradigm. The instruction tuned model is [LiveCC-7B-Instruct](https://huggingface.co/chenjoya/LiveCC-7B-Instruct).
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Quickstart
|
| 30 |
Like qwen-vl-utils, we offer a toolkit to help you handle various types of visual input more conveniently, **especially on video streaming inputs**. You can install it using the following command:
|
|
|
|
| 25 |
> [!Important]
|
| 26 |
> This is the base model, pre-trained on [Live-CC-5M](https://huggingface.co/datasets/chenjoya/Live-CC-5M) dataset only with our proposed streaming frame-words paradigm. The instruction tuned model is [LiveCC-7B-Instruct](https://huggingface.co/chenjoya/LiveCC-7B-Instruct).
|
| 27 |
|
| 28 |
+
## Training with Streaming Frame-Words Paradigm
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
|
| 33 |
## Quickstart
|
| 34 |
Like qwen-vl-utils, we offer a toolkit to help you handle various types of visual input more conveniently, **especially on video streaming inputs**. You can install it using the following command:
|