Hugging Face's logo

Felladrin
/
onnx-llama2_xs_460M_experimental

Text Generation
Transformers.js
ONNX
llama
Model card Files Community
Felladrin commited on
Commit
737676c
•
1 Parent(s): b58f314

Add models files

Browse files
Files changed (10) hide show
  1. config.json +27 -0
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. onnx/model.onnx +3 -0
  5. onnx/model_quantized.onnx +3 -0
  6. quantize_config.json +70 -0
  7. special_tokens_map.json +18 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +33 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ahxt/llama2_xs_460M_experimental",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
12
+ "layernorm_epsilon": 1e-05,
13
+ "max_position_embeddings": 1024,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 16,
16
+ "num_hidden_layers": 24,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "transformers_version": "4.33.2",
25
+ "use_cache": true,
26
+ "vocab_size": 50304
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.33.2"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ef2d77afaab8807b4c9065d70c41214dab44734cb233d4bca90f4b39a0541e
3
+ size 1848320690
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf11a15d5a2e6103567fe223e20216eb5d534594ea66546e61af7b719c19b62
3
+ size 463969775
quantize_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Where",
8
+ "Sigmoid",
9
+ "ConstantOfShape",
10
+ "Unsqueeze",
11
+ "Sub",
12
+ "Expand",
13
+ "Squeeze",
14
+ "Add",
15
+ "ReduceMean",
16
+ "Constant",
17
+ "MatMul",
18
+ "Range",
19
+ "Neg",
20
+ "Sqrt",
21
+ "Transpose",
22
+ "Shape",
23
+ "Less",
24
+ "Concat",
25
+ "Mul",
26
+ "Pow",
27
+ "Reshape",
28
+ "Cast",
29
+ "Div",
30
+ "Slice",
31
+ "Equal",
32
+ "Softmax",
33
+ "Gather"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "model": {
38
+ "op_types": [
39
+ "Where",
40
+ "Sigmoid",
41
+ "ConstantOfShape",
42
+ "Unsqueeze",
43
+ "Sub",
44
+ "Expand",
45
+ "Squeeze",
46
+ "Add",
47
+ "ReduceMean",
48
+ "Constant",
49
+ "MatMul",
50
+ "Range",
51
+ "Neg",
52
+ "Sqrt",
53
+ "Transpose",
54
+ "Shape",
55
+ "Less",
56
+ "Concat",
57
+ "Mul",
58
+ "Pow",
59
+ "Reshape",
60
+ "Cast",
61
+ "Div",
62
+ "Slice",
63
+ "Equal",
64
+ "Softmax",
65
+ "Gather"
66
+ ],
67
+ "weight_type": "QInt8"
68
+ }
69
+ }
70
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": "#",
10
+ "pad_token": "\"",
11
+ "unk_token": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ }
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff