Upload Qwen3ForSequenceClassification
Browse files- config.json +44 -8
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -4,10 +4,12 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"
|
|
|
|
|
|
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
-
"hidden_size":
|
| 11 |
"id2label": {
|
| 12 |
"0": "LABEL_0"
|
| 13 |
},
|
|
@@ -17,22 +19,56 @@
|
|
| 17 |
"LABEL_0": 0
|
| 18 |
},
|
| 19 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"full_attention",
|
| 21 |
"full_attention"
|
| 22 |
],
|
| 23 |
-
"max_position_embeddings":
|
| 24 |
-
"max_window_layers":
|
| 25 |
"model_type": "qwen3",
|
| 26 |
"num_attention_heads": 4,
|
| 27 |
"num_hidden_layers": 2,
|
| 28 |
"num_key_value_heads": 2,
|
| 29 |
"rms_norm_eps": 1e-06,
|
| 30 |
"rope_scaling": null,
|
| 31 |
-
"rope_theta":
|
| 32 |
"sliding_window": null,
|
| 33 |
-
"tie_word_embeddings":
|
| 34 |
-
"transformers_version": "4.
|
| 35 |
"use_cache": true,
|
| 36 |
"use_sliding_window": false,
|
| 37 |
-
"vocab_size":
|
| 38 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
"id2label": {
|
| 14 |
"0": "LABEL_0"
|
| 15 |
},
|
|
|
|
| 19 |
"LABEL_0": 0
|
| 20 |
},
|
| 21 |
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
"full_attention",
|
| 57 |
"full_attention"
|
| 58 |
],
|
| 59 |
+
"max_position_embeddings": 40960,
|
| 60 |
+
"max_window_layers": 36,
|
| 61 |
"model_type": "qwen3",
|
| 62 |
"num_attention_heads": 4,
|
| 63 |
"num_hidden_layers": 2,
|
| 64 |
"num_key_value_heads": 2,
|
| 65 |
"rms_norm_eps": 1e-06,
|
| 66 |
"rope_scaling": null,
|
| 67 |
+
"rope_theta": 1000000,
|
| 68 |
"sliding_window": null,
|
| 69 |
+
"tie_word_embeddings": true,
|
| 70 |
+
"transformers_version": "4.56.2",
|
| 71 |
"use_cache": true,
|
| 72 |
"use_sliding_window": false,
|
| 73 |
+
"vocab_size": 151936
|
| 74 |
}
|
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 sha256:4c93aade12b3da3cc0cc83191b8bb8020a02bbf1140baee9f07075f6b5c8f216
|
| 3 |
+
size 4970248
|