Upload Qwen3ForSequenceClassification
Browse files- config.json +32 -2
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
|
@@ -16,6 +17,36 @@
|
|
| 16 |
"label2id": {
|
| 17 |
"LABEL_0": 0
|
| 18 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"max_position_embeddings": 40960,
|
| 20 |
"max_window_layers": 28,
|
| 21 |
"model_type": "qwen3",
|
|
@@ -28,8 +59,7 @@
|
|
| 28 |
"rope_theta": 1000000,
|
| 29 |
"sliding_window": null,
|
| 30 |
"tie_word_embeddings": true,
|
| 31 |
-
"
|
| 32 |
-
"transformers_version": "4.51.0",
|
| 33 |
"unsloth_fixed": true,
|
| 34 |
"use_cache": false,
|
| 35 |
"use_sliding_window": false,
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
|
|
|
| 17 |
"label2id": {
|
| 18 |
"LABEL_0": 0
|
| 19 |
},
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
"max_position_embeddings": 40960,
|
| 51 |
"max_window_layers": 28,
|
| 52 |
"model_type": "qwen3",
|
|
|
|
| 59 |
"rope_theta": 1000000,
|
| 60 |
"sliding_window": null,
|
| 61 |
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.57.1",
|
|
|
|
| 63 |
"unsloth_fixed": true,
|
| 64 |
"use_cache": false,
|
| 65 |
"use_sliding_window": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2384239152
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06301302b9b6ae5a3e4a2ffacf008519e237425cd8ba1205e1d74a7ef9417cf0
|
| 3 |
size 2384239152
|