Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,10 @@ language:
|
|
| 4 |
- hu
|
| 5 |
base_model:
|
| 6 |
- state-spaces/mamba-130m-hf
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# PULI-HuBA130M
|
|
@@ -36,7 +40,7 @@ MambaForCausalLM(
|
|
| 36 |
|
| 37 |
## Training Data (Pretraining)
|
| 38 |
|
| 39 |
-
|
| 40 |
|
| 41 |
## Training Details
|
| 42 |
|
|
|
|
| 4 |
- hu
|
| 5 |
base_model:
|
| 6 |
- state-spaces/mamba-130m-hf
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- Transformers
|
| 10 |
+
- mamba
|
| 11 |
---
|
| 12 |
|
| 13 |
# PULI-HuBA130M
|
|
|
|
| 40 |
|
| 41 |
## Training Data (Pretraining)
|
| 42 |
|
| 43 |
+
The model was trained on a ~3.48B-token, toxic-filtered, deduplicated, and semantically segmented dataset.
|
| 44 |
|
| 45 |
## Training Details
|
| 46 |
|