Add library name to metadata and link to the paper
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
- zh
|
|
@@ -9,10 +10,10 @@ language:
|
|
| 9 |
- ar
|
| 10 |
- es
|
| 11 |
- pt
|
|
|
|
|
|
|
| 12 |
metrics:
|
| 13 |
- accuracy
|
| 14 |
-
base_model:
|
| 15 |
-
- BlinkDL/rwkv-7-world
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
---
|
| 18 |
|
|
@@ -24,7 +25,6 @@ This is RWKV-7 model under flash-linear attention format.
|
|
| 24 |
|
| 25 |
## Model Details
|
| 26 |
|
| 27 |
-
|
| 28 |
### Model Description
|
| 29 |
|
| 30 |
<!-- Provide a longer summary of what this model is. -->
|
|
@@ -100,7 +100,6 @@ This model is trained on the World v3 with a total of 3.119 trillion tokens.
|
|
| 100 |
|
| 101 |
- **Training regime:** bfloat16, lr 4e-4 to 1e-5 "delayed" cosine decay, wd 0.1 (with increasing batch sizes during the middle)
|
| 102 |
|
| 103 |
-
|
| 104 |
## FAQ
|
| 105 |
Q: safetensors metadata is none.
|
| 106 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- BlinkDL/rwkv-7-world
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
- zh
|
|
|
|
| 10 |
- ar
|
| 11 |
- es
|
| 12 |
- pt
|
| 13 |
+
license: apache-2.0
|
| 14 |
+
library_name: transformers
|
| 15 |
metrics:
|
| 16 |
- accuracy
|
|
|
|
|
|
|
| 17 |
pipeline_tag: text-generation
|
| 18 |
---
|
| 19 |
|
|
|
|
| 25 |
|
| 26 |
## Model Details
|
| 27 |
|
|
|
|
| 28 |
### Model Description
|
| 29 |
|
| 30 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
|
| 100 |
|
| 101 |
- **Training regime:** bfloat16, lr 4e-4 to 1e-5 "delayed" cosine decay, wd 0.1 (with increasing batch sizes during the middle)
|
| 102 |
|
|
|
|
| 103 |
## FAQ
|
| 104 |
Q: safetensors metadata is none.
|
| 105 |
|