Update README.md
Browse files
README.md
CHANGED
|
@@ -4,10 +4,14 @@ base_model:
|
|
| 4 |
- RWKV-Red-Team/ARWKV-7B-Preview-0.1
|
| 5 |
---
|
| 6 |
|
| 7 |
-
This model only works with RWKV-Infer and RWKV-LM-RLHF
|
|
|
|
| 8 |
|
| 9 |
slightly fine-tuned CJE 900k including Deepseek R1 magpie.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
| 11 |
if you want use reasoning mode, set system prompts below
|
| 12 |
|
| 13 |
```
|
|
|
|
| 4 |
- RWKV-Red-Team/ARWKV-7B-Preview-0.1
|
| 5 |
---
|
| 6 |
|
| 7 |
+
This model only works with RWKV-Infer and RWKV-LM-RLHF.
|
| 8 |
+
This is a completely early model. No warranty. Use at your own risk.
|
| 9 |
|
| 10 |
slightly fine-tuned CJE 900k including Deepseek R1 magpie.
|
| 11 |
|
| 12 |
+
v7 FLA ctx5120, 1k slided overlap training. SFT(with loss smooting=0.001)
|
| 13 |
+
DoRA(total 0.5B parameters), Emb frozen.
|
| 14 |
+
|
| 15 |
if you want use reasoning mode, set system prompts below
|
| 16 |
|
| 17 |
```
|