Upload optimized model
Browse files- README.md +15 -0
- config.json +64 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- quantized
|
| 4 |
+
- ner
|
| 5 |
+
- 8-bit
|
| 6 |
+
library_name: optimum
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Model - sadsacsasac-optimized
|
| 10 |
+
|
| 11 |
+
This model has been optimized and uploaded to the HuggingFace Hub.
|
| 12 |
+
|
| 13 |
+
## Model Details
|
| 14 |
+
- Original Repository: sadsacsasac-optimized
|
| 15 |
+
- Optimization Tags: quantized, ner, 8-bit
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dslim/bert-base-NER",
|
| 3 |
+
"_num_labels": 9,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "O",
|
| 14 |
+
"1": "B-MISC",
|
| 15 |
+
"2": "I-MISC",
|
| 16 |
+
"3": "B-PER",
|
| 17 |
+
"4": "I-PER",
|
| 18 |
+
"5": "B-ORG",
|
| 19 |
+
"6": "I-ORG",
|
| 20 |
+
"7": "B-LOC",
|
| 21 |
+
"8": "I-LOC"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"B-LOC": 7,
|
| 27 |
+
"B-MISC": 1,
|
| 28 |
+
"B-ORG": 5,
|
| 29 |
+
"B-PER": 3,
|
| 30 |
+
"I-LOC": 8,
|
| 31 |
+
"I-MISC": 2,
|
| 32 |
+
"I-ORG": 6,
|
| 33 |
+
"I-PER": 4,
|
| 34 |
+
"O": 0
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"max_position_embeddings": 512,
|
| 38 |
+
"model_type": "bert",
|
| 39 |
+
"num_attention_heads": 12,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"output_past": true,
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"position_embedding_type": "absolute",
|
| 44 |
+
"quantization_config": {
|
| 45 |
+
"_load_in_4bit": false,
|
| 46 |
+
"_load_in_8bit": true,
|
| 47 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 48 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 49 |
+
"bnb_4bit_quant_type": "fp4",
|
| 50 |
+
"bnb_4bit_use_double_quant": false,
|
| 51 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 52 |
+
"llm_int8_has_fp16_weight": false,
|
| 53 |
+
"llm_int8_skip_modules": null,
|
| 54 |
+
"llm_int8_threshold": 6.0,
|
| 55 |
+
"load_in_4bit": false,
|
| 56 |
+
"load_in_8bit": true,
|
| 57 |
+
"quant_method": "bitsandbytes"
|
| 58 |
+
},
|
| 59 |
+
"torch_dtype": "float16",
|
| 60 |
+
"transformers_version": "4.47.1",
|
| 61 |
+
"type_vocab_size": 2,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 28996
|
| 64 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9fee5aeb45b3f26a441efbd9a2cbcc63aceb0157457d17e548ac8b958e5e06a
|
| 3 |
+
size 130889650
|