Improve metadata 🤗
#3
by
merve
HF Staff
- opened
README.md
CHANGED
|
@@ -4,6 +4,8 @@ language:
|
|
| 4 |
license: apache-2.0
|
| 5 |
base_model:
|
| 6 |
- Qwen/Qwen3-32B
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
# T-pro-it-2.0
|
| 9 |
|
|
@@ -297,4 +299,4 @@ T-pro-it-2.0 natively supports a context length of 32,768 tokens.
|
|
| 297 |
For conversations where the input significantly exceeds this limit, follow the recommendations from the [Qwen3 model card](https://huggingface.co/Qwen/Qwen3-235B-A22B#processing-long-texts) on processing long texts.
|
| 298 |
|
| 299 |
For example, in SGLang, you can enable 128K context support with the following command:
|
| 300 |
-
`llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768`
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
base_model:
|
| 6 |
- Qwen/Qwen3-32B
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
---
|
| 10 |
# T-pro-it-2.0
|
| 11 |
|
|
|
|
| 299 |
For conversations where the input significantly exceeds this limit, follow the recommendations from the [Qwen3 model card](https://huggingface.co/Qwen/Qwen3-235B-A22B#processing-long-texts) on processing long texts.
|
| 300 |
|
| 301 |
For example, in SGLang, you can enable 128K context support with the following command:
|
| 302 |
+
`llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768`
|