Drop the metadata start_token (weights unchanged)
Browse filesThe metadata start_token held the literal string "None" (this tokenizer has no BOS), and the engine resolved it to a real vocabulary token - so every prompt began with the word "None", a stream the model was never trained on.
Metadata-only change: every tokenizer and TFLite section is byte-identical to the previous file (verified by sha256 per section), so quality and speed are unchanged and the card's measured numbers still stand.
- .gitattributes +1 -0
- SmolLM3-3B.litertlm +2 -2
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
model.litertlm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
SmolLM3-3B_q4_block32_ekv4096.litertlm filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
model.litertlm filter=lfs diff=lfs merge=lfs -text
|
| 37 |
SmolLM3-3B_q4_block32_ekv4096.litertlm filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
SmolLM3-3B.litertlm filter=lfs diff=lfs merge=lfs -text
|
SmolLM3-3B.litertlm
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 sha256:43d0549b235cf009a4c316f6d0bf703eddcd701f22bc3d2b6b46396d0dbe9c63
|
| 3 |
+
size 3108967664
|