Hugging Face's logo

damerajee
/
tiny-Openhathiv4

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
 Community
damerajee commited on
Commit
95d4825
·
verified ·
1 Parent(s): f5e6f15

Upload folder using huggingface_hub

Browse files

Uploading initialised weights and configs

Files changed (8) hide show
  1. config.json +28 -0
  2. generation_config.json +10 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +118 -0
  6. special_tokens_map.json +24 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +49 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sarvamai/OpenHathi-7B-Hi-v0.1-Base",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 12,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": true,
27
+ "vocab_size": 48064
28
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.01,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.40.2"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827b795996ae042ec618ef934846a38bedcf99686b6ace6fceff3f30abc84df1
3
+ size 4980403992
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c41d0e83cc80d0ea2f5d01db59c09ac82e1f261e528b4e1adf38a85b64878ec
3
+ size 664298256
model.safetensors.index.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5644689408
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.norm.weight": "model-00002-of-00002.safetensors"
117
+ }
118
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[PAD]",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "[PAD]",
44
+ "sp_model_kwargs": {},
45
+ "spaces_between_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": false
49
+ }