Upload BloomForTokenClassification
Browse files- config.json +72 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloom-1b7",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5",
|
| 21 |
+
"6": "LABEL_6",
|
| 22 |
+
"7": "LABEL_7",
|
| 23 |
+
"8": "LABEL_8",
|
| 24 |
+
"9": "LABEL_9",
|
| 25 |
+
"10": "LABEL_10",
|
| 26 |
+
"11": "LABEL_11"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"label2id": {
|
| 30 |
+
"LABEL_0": 0,
|
| 31 |
+
"LABEL_1": 1,
|
| 32 |
+
"LABEL_10": 10,
|
| 33 |
+
"LABEL_11": 11,
|
| 34 |
+
"LABEL_2": 2,
|
| 35 |
+
"LABEL_3": 3,
|
| 36 |
+
"LABEL_4": 4,
|
| 37 |
+
"LABEL_5": 5,
|
| 38 |
+
"LABEL_6": 6,
|
| 39 |
+
"LABEL_7": 7,
|
| 40 |
+
"LABEL_8": 8,
|
| 41 |
+
"LABEL_9": 9
|
| 42 |
+
},
|
| 43 |
+
"layer_norm_epsilon": 1e-05,
|
| 44 |
+
"masked_softmax_fusion": true,
|
| 45 |
+
"model_type": "bloom",
|
| 46 |
+
"n_head": 16,
|
| 47 |
+
"n_inner": null,
|
| 48 |
+
"n_layer": 24,
|
| 49 |
+
"offset_alibi": 100,
|
| 50 |
+
"pad_token_id": 3,
|
| 51 |
+
"pretraining_tp": 2,
|
| 52 |
+
"quantization_config": {
|
| 53 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 54 |
+
"bnb_4bit_quant_type": "fp4",
|
| 55 |
+
"bnb_4bit_use_double_quant": false,
|
| 56 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 57 |
+
"llm_int8_has_fp16_weight": false,
|
| 58 |
+
"llm_int8_skip_modules": null,
|
| 59 |
+
"llm_int8_threshold": 6.0,
|
| 60 |
+
"load_in_4bit": false,
|
| 61 |
+
"load_in_8bit": true
|
| 62 |
+
},
|
| 63 |
+
"seq_length": 4096,
|
| 64 |
+
"skip_bias_add": true,
|
| 65 |
+
"skip_bias_add_qkv": false,
|
| 66 |
+
"slow_but_exact": false,
|
| 67 |
+
"torch_dtype": "float16",
|
| 68 |
+
"transformers_version": "4.30.0.dev0",
|
| 69 |
+
"unk_token_id": 0,
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 250880
|
| 72 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b033056597fd7eb872aa7170103bdd057fc40b49155a787884200e0b8f18459
|
| 3 |
+
size 2238808937
|