Mohmmad-Dev commited on
Commit
8da1beb
1 Parent(s): c2212e3

Upload 6 files

Browse files
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6112ae7c1b22b6c312b5fabf7a2eb42c01c924ffda7358b4658cfeb715580f56
3
+ size 466952136
stella_en_400M_v5.gguf_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dunzhang/stella_en_400M_v5",
3
+ "architectures": [
4
+ "NewModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "dunzhang/stella_en_400M_v5--configuration.NewConfig",
9
+ "AutoModel": "dunzhang/stella_en_400M_v5--modeling.NewModel"
10
+ },
11
+ "classifier_dropout": null,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "layer_norm_eps": 1e-12,
18
+ "layer_norm_type": "layer_norm",
19
+ "logn_attention_clip1": false,
20
+ "logn_attention_scale": false,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "new",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 24,
25
+ "pack_qkv": true,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "rope",
28
+ "quantization_config": {
29
+ "_load_in_4bit": false,
30
+ "_load_in_8bit": true,
31
+ "bnb_4bit_compute_dtype": "float32",
32
+ "bnb_4bit_quant_storage": "uint8",
33
+ "bnb_4bit_quant_type": "fp4",
34
+ "bnb_4bit_use_double_quant": false,
35
+ "llm_int8_enable_fp32_cpu_offload": false,
36
+ "llm_int8_has_fp16_weight": false,
37
+ "llm_int8_skip_modules": null,
38
+ "llm_int8_threshold": 6.0,
39
+ "load_in_4bit": false,
40
+ "load_in_8bit": true,
41
+ "quant_method": "bitsandbytes"
42
+ },
43
+ "rope_scaling": {
44
+ "factor": 2.0,
45
+ "type": "ntk"
46
+ },
47
+ "rope_theta": 160000,
48
+ "torch_dtype": "float16",
49
+ "transformers_version": "4.42.4",
50
+ "type_vocab_size": 2,
51
+ "unpad_inputs": true,
52
+ "use_memory_efficient_attention": true,
53
+ "vocab_size": 30528
54
+ }
stella_en_400M_v5.gguf_special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
stella_en_400M_v5.gguf_tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
stella_en_400M_v5.gguf_tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
stella_en_400M_v5.gguf_vocab.txt ADDED
The diff for this file is too large to render. See raw diff