Update README.md
Browse files
README.md
CHANGED
|
@@ -81,9 +81,15 @@ Performance evaluation is ongoing. The model shows promising results in:
|
|
| 81 |
- Significantly improved needle-in-haystack task performance compared to pure RWKV architectures
|
| 82 |
- Competitive performance on standard language modeling benchmarks
|
| 83 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
## Usage with Hugging Face Transformers
|
| 85 |
|
| 86 |
-
|
|
|
|
|
|
|
| 87 |
|
| 88 |
## Code Repositories
|
| 89 |
|
|
|
|
| 81 |
- Significantly improved needle-in-haystack task performance compared to pure RWKV architectures
|
| 82 |
- Competitive performance on standard language modeling benchmarks
|
| 83 |
|
| 84 |
+
## Usage with RWKV-Infer
|
| 85 |
+
- **RWKV-Infer** Triton based Hybrid RWKV Inference engine, can be check at: [https://github.com/OpenMOSE/RWKV-Infer/wiki/How-to-Running-RWKV-hxa079-models%3F](https://github.com/OpenMOSE/RWKV-Infer/wiki/How-to-Running-RWKV-hxa079-models%3F)
|
| 86 |
+
|
| 87 |
+
|
| 88 |
## Usage with Hugging Face Transformers
|
| 89 |
|
| 90 |
+
Currently in development. stay tuned :)
|
| 91 |
+
|
| 92 |
+
|
| 93 |
|
| 94 |
## Code Repositories
|
| 95 |
|