Upload Gemma3TextForSequenceClassification
Browse files- config.json +38 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3TextForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 8,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 32,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 64,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention"
|
| 21 |
+
],
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "gemma3_text",
|
| 24 |
+
"num_attention_heads": 4,
|
| 25 |
+
"num_hidden_layers": 2,
|
| 26 |
+
"num_key_value_heads": 2,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"query_pre_attn_scalar": 8,
|
| 29 |
+
"rms_norm_eps": 1e-06,
|
| 30 |
+
"rope_local_base_freq": 10000.0,
|
| 31 |
+
"rope_scaling": null,
|
| 32 |
+
"rope_theta": 10000.0,
|
| 33 |
+
"sliding_window": 128,
|
| 34 |
+
"transformers_version": "4.57.3",
|
| 35 |
+
"use_bidirectional_attention": false,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 1024
|
| 38 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eadb1a2623cd699fca95e7df584fdbfd3d3d61bd2717f7ffa3ffad528027000
|
| 3 |
+
size 209320
|