Commit
•
cda0305
1
Parent(s):
619f61b
Update tiny models for StableLmForSequenceClassification
Browse files- config.json +3 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -20,13 +20,15 @@
|
|
| 20 |
"num_key_value_heads": 4,
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"partial_rotary_factor": 0.25,
|
|
|
|
| 23 |
"rope_scaling": null,
|
| 24 |
"rope_theta": 10000,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "float32",
|
| 27 |
-
"transformers_version": "4.
|
| 28 |
"type_vocab_size": 16,
|
| 29 |
"use_cache": true,
|
|
|
|
| 30 |
"use_qkv_bias": false,
|
| 31 |
"vocab_size": 1024
|
| 32 |
}
|
|
|
|
| 20 |
"num_key_value_heads": 4,
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"partial_rotary_factor": 0.25,
|
| 23 |
+
"qk_layernorm": false,
|
| 24 |
"rope_scaling": null,
|
| 25 |
"rope_theta": 10000,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.40.0.dev0",
|
| 29 |
"type_vocab_size": 16,
|
| 30 |
"use_cache": true,
|
| 31 |
+
"use_parallel_residual": false,
|
| 32 |
"use_qkv_bias": false,
|
| 33 |
"vocab_size": 1024
|
| 34 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 455752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba8566ac0ff1c8b470e85313629016922d33d28d3391373e1dfb1b5537c49ecb
|
| 3 |
size 455752
|