Update README.md

README.md

@@ -5,14 +5,18 @@ license: other
 license_name: cc-by-nc-4.0-weights-apache-2.0-code
 license_link: LICENSE.md
 tags:
-  - mamba2
-  - byte-level
-  - state-space-model
-  - multimodal
-  - custom-code
-  - causal-lm
+- mamba2
+- byte-level
+- multimodal
+- custom-code
+- base_model
 language:
-  - en
+- en
+datasets:
+- HuggingFaceM4/FineVision
+- HuggingFaceFW/finepdfs
+- HuggingFaceFW/fineweb-edu
+- webshart/suno-various-94k
 ---
 
 # Three-Level Nested Byte Mamba-2
@@ -33,6 +37,7 @@ The published weights are sharded SafeTensors containing only the 980 model tens
 - Source checkpoint step: **889,000**
 - Recommended runtime precision: **BF16**
 - Recommended placement: fine/decoder on `cuda:0`, level 2 on `cuda:1`, level 3 on `cuda:2`
+- Last training count: 15GB **Absoloutly undertrained**
 
 The source checkpoint step is documentation only; it is not embedded in the SafeTensors weights or inference configuration.
 
@@ -207,4 +212,4 @@ datasets and third-party content are not covered by either grant. See
 - `nested_inference_tools.py`: SafeTensors loading, state caching, and sampling
 - `infer_nested_model.py`: command-line generator
 - `architecture.svg`: architecture visualization
-- `LICENSE.md`: weight, documentation, and code license scope
+- `LICENSE.md`: weight, documentation, and code license scope