Upload AlbertForSequenceClassification
Browse files- config.json +66 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert/albert-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"gap_size": 0,
|
| 13 |
+
"hidden_act": "gelu_new",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1",
|
| 19 |
+
"2": "LABEL_2",
|
| 20 |
+
"3": "LABEL_3",
|
| 21 |
+
"4": "LABEL_4",
|
| 22 |
+
"5": "LABEL_5",
|
| 23 |
+
"6": "LABEL_6"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"inner_group_num": 1,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"LABEL_0": 0,
|
| 30 |
+
"LABEL_1": 1,
|
| 31 |
+
"LABEL_2": 2,
|
| 32 |
+
"LABEL_3": 3,
|
| 33 |
+
"LABEL_4": 4,
|
| 34 |
+
"LABEL_5": 5,
|
| 35 |
+
"LABEL_6": 6
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"model_type": "albert",
|
| 40 |
+
"net_structure_type": 0,
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hidden_groups": 1,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"num_memory_blocks": 0,
|
| 45 |
+
"pad_token_id": 0,
|
| 46 |
+
"position_embedding_type": "absolute",
|
| 47 |
+
"quantization_config": {
|
| 48 |
+
"_load_in_4bit": false,
|
| 49 |
+
"_load_in_8bit": true,
|
| 50 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 51 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 52 |
+
"bnb_4bit_quant_type": "fp4",
|
| 53 |
+
"bnb_4bit_use_double_quant": false,
|
| 54 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 55 |
+
"llm_int8_has_fp16_weight": false,
|
| 56 |
+
"llm_int8_skip_modules": null,
|
| 57 |
+
"llm_int8_threshold": 6.0,
|
| 58 |
+
"load_in_4bit": false,
|
| 59 |
+
"load_in_8bit": true,
|
| 60 |
+
"quant_method": "bitsandbytes"
|
| 61 |
+
},
|
| 62 |
+
"torch_dtype": "float16",
|
| 63 |
+
"transformers_version": "4.45.1",
|
| 64 |
+
"type_vocab_size": 2,
|
| 65 |
+
"vocab_size": 30000
|
| 66 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:787fbfdca144195b13e3374155c16833626dbd5a97f1ce6cbdac2c4450a762cd
|
| 3 |
+
size 15651134
|