Add model card with tags for dsv3_0.5b
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
model_name: dsv3_0.5b
|
| 3 |
+
tags:
|
| 4 |
+
- yulanmini
|
| 5 |
+
- hybrid
|
| 6 |
+
- mamba
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# dsv3_0.5b
|
| 10 |
+
|
| 11 |
+
This is a model uploaded from /mnt/nanjingcephfs/project_wx-rec-alg-bdc-exp/bwzheng/yulan/hyw/megatron_lm_workspace/log/metadata-url-2025.09.09-16.56.04_dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-3.0e-5-bs-1024-gpus-32-seqlen-8192.
|