v8: continued training to 2.6B tokens (from 1.51B). Improved coherence on narrative prompts. Same architecture (10,052,864 params, 5L d320 5-head SwiGLU RoPE).
#14
by Compactbot - opened
- model.safetensors +2 -2
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c3ce3c6c4ac2561c5be3c27f3a12a7a8272338cfee74e29d02bb8826bb6f798
|
| 3 |
+
size 41142232
|