mohitsha HF staff commited on
Commit
7033c10
1 Parent(s): ad3afa0

Upload 11 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 1
4
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "opt-125m_smoothquant\\onnx",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "transformers_version": "4.34.0",
27
+ "use_cache": true,
28
+ "vocab_size": 50272,
29
+ "word_embed_proj_dim": 768
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.34.0"
7
+ }
grouped_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8574ec62c7f537d735b4a909c2c117ce09d7f27b55518b643d7d5956538d20dc
3
+ size 306574717
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f95711ceb6e23cc0634ca4987fd1d53650a4de0230b309363744678a6029dc0
3
+ size 285338093
ort_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "one_external_file": true,
3
+ "opset": null,
4
+ "optimization": {},
5
+ "optimum_version": "1.14.0",
6
+ "quantization": {
7
+ "activations_dtype": "QUInt8",
8
+ "activations_symmetric": true,
9
+ "format": "QOperator",
10
+ "is_static": false,
11
+ "mode": "IntegerOps",
12
+ "nodes_to_exclude": [],
13
+ "nodes_to_quantize": [],
14
+ "operators_to_quantize": [
15
+ "MatMul"
16
+ ],
17
+ "per_channel": false,
18
+ "qdq_add_pair_to_weight": false,
19
+ "qdq_dedicated_pair": false,
20
+ "qdq_op_type_per_channel_support_to_axis": {
21
+ "MatMul": 1
22
+ },
23
+ "reduce_range": false,
24
+ "weights_dtype": "QInt8",
25
+ "weights_symmetric": true
26
+ },
27
+ "transformers_version": "4.34.0",
28
+ "use_external_data_format": false
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "</s>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "additional_special_tokens": [],
23
+ "bos_token": "</s>",
24
+ "clean_up_tokenization_spaces": true,
25
+ "eos_token": "</s>",
26
+ "errors": "replace",
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "pad_token": "<pad>",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff