Hugging Face's logo

Defetya
/
qwen-1.8B-saiga

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Defetya commited on
Commit
2c99336
•
1 Parent(s): cb68a6d

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +140 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +40 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "attention_partition_spec": [
7
+ [
8
+ "dp",
9
+ "fsdp"
10
+ ],
11
+ "sp",
12
+ "tp",
13
+ null
14
+ ],
15
+ "attn_mechanism": "normal",
16
+ "axis_dims": [
17
+ 1,
18
+ -1,
19
+ 1,
20
+ 1
21
+ ],
22
+ "axis_names": [
23
+ "dp",
24
+ "fsdp",
25
+ "tp",
26
+ "sp"
27
+ ],
28
+ "backend": null,
29
+ "bias_partition_spec": [
30
+ [
31
+ "dp",
32
+ "fsdp"
33
+ ],
34
+ null,
35
+ null,
36
+ null
37
+ ],
38
+ "bits": null,
39
+ "block_b": 1,
40
+ "block_k": 128,
41
+ "block_k_dkv": 128,
42
+ "block_k_dq": 128,
43
+ "block_k_major": 128,
44
+ "block_k_major_dkv": 128,
45
+ "block_k_major_dq": 128,
46
+ "block_q": 128,
47
+ "block_q_dkv": 128,
48
+ "block_q_dq": 128,
49
+ "block_q_major_dkv": 128,
50
+ "bos_token_id": 151643,
51
+ "easy_method": "train",
52
+ "embd_pdrop": 0.0,
53
+ "eos_token_id": 151645,
54
+ "fcm_max_ratio": 0.0,
55
+ "fcm_min_ratio": 0.0,
56
+ "generation_attention_partition_spec": [
57
+ [
58
+ "dp",
59
+ "fsdp"
60
+ ],
61
+ null,
62
+ "tp",
63
+ null
64
+ ],
65
+ "generation_bias_partition_spec": [
66
+ [
67
+ "dp",
68
+ "fsdp"
69
+ ],
70
+ null,
71
+ null,
72
+ null
73
+ ],
74
+ "generation_query_partition_spec": [
75
+ [
76
+ "dp",
77
+ "fsdp"
78
+ ],
79
+ "sp",
80
+ null,
81
+ null
82
+ ],
83
+ "hidden_act": "silu",
84
+ "hidden_size": 2048,
85
+ "initializer_range": 0.02,
86
+ "intermediate_size": 5504,
87
+ "key_partition_spec": [
88
+ [
89
+ "dp",
90
+ "fsdp"
91
+ ],
92
+ "sp",
93
+ "tp",
94
+ null
95
+ ],
96
+ "max_position_embeddings": 32768,
97
+ "max_window_layers": 21,
98
+ "model_type": "qwen2",
99
+ "num_attention_heads": 16,
100
+ "num_hidden_layers": 24,
101
+ "num_key_value_heads": 16,
102
+ "number_rep_kv": 1,
103
+ "query_partition_spec": [
104
+ [
105
+ "dp",
106
+ "fsdp"
107
+ ],
108
+ "sp",
109
+ "tp",
110
+ null
111
+ ],
112
+ "resid_pdrop": 0.0,
113
+ "rms_norm_eps": 1e-06,
114
+ "rope_scaling": null,
115
+ "rope_theta": 10000.0,
116
+ "scan_attention_layers": false,
117
+ "scan_layers": true,
118
+ "scan_mlp_chunk_size": 1024,
119
+ "scan_ring_attention": false,
120
+ "shard_attention_computation": true,
121
+ "sliding_window": 32768,
122
+ "tie_word_embeddings": false,
123
+ "torch_dtype": "float16",
124
+ "transformers_version": "4.40.0.dev0",
125
+ "use_cache": true,
126
+ "use_scan_mlp": false,
127
+ "use_sharded_kv_caching": true,
128
+ "use_sharding_constraint": false,
129
+ "use_sliding_window": false,
130
+ "value_partition_spec": [
131
+ [
132
+ "dp",
133
+ "fsdp"
134
+ ],
135
+ "sp",
136
+ "tp",
137
+ null
138
+ ],
139
+ "vocab_size": 151936
140
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83451b07e11eaf2f86a4bf6e1c2d91a8cdba77e8f05e07b5ceeb2d1101d093c8
3
+ size 3673690400
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
30
+ "bos_token": null,
31
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|im_end|>",
34
+ "errors": "replace",
35
+ "model_max_length": 32768,
36
+ "pad_token": "<|endoftext|>",
37
+ "split_special_tokens": false,
38
+ "tokenizer_class": "Qwen2Tokenizer",
39
+ "unk_token": null
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff