Hugging Face's logo

lakpriya
/
llama_1b_onnx

ONNX
llama
Model card Files Community
lakpriya commited on
Commit
7939da2
·
verified ·
1 Parent(s): 5ab7fa3

Add new files to repository

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +114 -0
  2. config.json +39 -0
  3. generation_config.json +12 -0
  4. model.embed_tokens.weight +3 -0
  5. model.layers.0.input_layernorm.weight +0 -0
  6. model.layers.0.post_attention_layernorm.weight +0 -0
  7. model.layers.1.input_layernorm.weight +0 -0
  8. model.layers.1.post_attention_layernorm.weight +0 -0
  9. model.layers.10.input_layernorm.weight +0 -0
  10. model.layers.10.post_attention_layernorm.weight +0 -0
  11. model.layers.11.input_layernorm.weight +0 -0
  12. model.layers.11.post_attention_layernorm.weight +0 -0
  13. model.layers.12.input_layernorm.weight +0 -0
  14. model.layers.12.post_attention_layernorm.weight +0 -0
  15. model.layers.13.input_layernorm.weight +0 -0
  16. model.layers.13.post_attention_layernorm.weight +0 -0
  17. model.layers.14.input_layernorm.weight +0 -0
  18. model.layers.14.post_attention_layernorm.weight +0 -0
  19. model.layers.15.input_layernorm.weight +0 -0
  20. model.layers.15.post_attention_layernorm.weight +0 -0
  21. model.layers.2.input_layernorm.weight +0 -0
  22. model.layers.2.post_attention_layernorm.weight +0 -0
  23. model.layers.3.input_layernorm.weight +0 -0
  24. model.layers.3.post_attention_layernorm.weight +0 -0
  25. model.layers.4.input_layernorm.weight +0 -0
  26. model.layers.4.post_attention_layernorm.weight +0 -0
  27. model.layers.5.input_layernorm.weight +0 -0
  28. model.layers.5.post_attention_layernorm.weight +0 -0
  29. model.layers.6.input_layernorm.weight +0 -0
  30. model.layers.6.post_attention_layernorm.weight +0 -0
  31. model.layers.7.input_layernorm.weight +0 -0
  32. model.layers.7.post_attention_layernorm.weight +0 -0
  33. model.layers.8.input_layernorm.weight +0 -0
  34. model.layers.8.post_attention_layernorm.weight +0 -0
  35. model.layers.9.input_layernorm.weight +0 -0
  36. model.layers.9.post_attention_layernorm.weight +0 -0
  37. model.norm.weight +0 -0
  38. model.onnx +3 -0
  39. model_quantized.onnx +3 -0
  40. onnx__MatMul_4851 +3 -0
  41. onnx__MatMul_4852 +3 -0
  42. onnx__MatMul_4853 +3 -0
  43. onnx__MatMul_4878 +3 -0
  44. onnx__MatMul_4879 +3 -0
  45. onnx__MatMul_4880 +3 -0
  46. onnx__MatMul_4881 +3 -0
  47. onnx__MatMul_4882 +3 -0
  48. onnx__MatMul_4883 +3 -0
  49. onnx__MatMul_4884 +3 -0
  50. onnx__MatMul_4909 +3 -0
.gitattributes CHANGED
@@ -33,3 +33,117 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.embed_tokens.weight filter=lfs diff=lfs merge=lfs -text
37
+ onnx__MatMul_4851 filter=lfs diff=lfs merge=lfs -text
38
+ onnx__MatMul_4852 filter=lfs diff=lfs merge=lfs -text
39
+ onnx__MatMul_4853 filter=lfs diff=lfs merge=lfs -text
40
+ onnx__MatMul_4878 filter=lfs diff=lfs merge=lfs -text
41
+ onnx__MatMul_4879 filter=lfs diff=lfs merge=lfs -text
42
+ onnx__MatMul_4880 filter=lfs diff=lfs merge=lfs -text
43
+ onnx__MatMul_4881 filter=lfs diff=lfs merge=lfs -text
44
+ onnx__MatMul_4882 filter=lfs diff=lfs merge=lfs -text
45
+ onnx__MatMul_4883 filter=lfs diff=lfs merge=lfs -text
46
+ onnx__MatMul_4884 filter=lfs diff=lfs merge=lfs -text
47
+ onnx__MatMul_4909 filter=lfs diff=lfs merge=lfs -text
48
+ onnx__MatMul_4910 filter=lfs diff=lfs merge=lfs -text
49
+ onnx__MatMul_4911 filter=lfs diff=lfs merge=lfs -text
50
+ onnx__MatMul_4912 filter=lfs diff=lfs merge=lfs -text
51
+ onnx__MatMul_4913 filter=lfs diff=lfs merge=lfs -text
52
+ onnx__MatMul_4914 filter=lfs diff=lfs merge=lfs -text
53
+ onnx__MatMul_4915 filter=lfs diff=lfs merge=lfs -text
54
+ onnx__MatMul_4940 filter=lfs diff=lfs merge=lfs -text
55
+ onnx__MatMul_4941 filter=lfs diff=lfs merge=lfs -text
56
+ onnx__MatMul_4942 filter=lfs diff=lfs merge=lfs -text
57
+ onnx__MatMul_4943 filter=lfs diff=lfs merge=lfs -text
58
+ onnx__MatMul_4944 filter=lfs diff=lfs merge=lfs -text
59
+ onnx__MatMul_4945 filter=lfs diff=lfs merge=lfs -text
60
+ onnx__MatMul_4946 filter=lfs diff=lfs merge=lfs -text
61
+ onnx__MatMul_4971 filter=lfs diff=lfs merge=lfs -text
62
+ onnx__MatMul_4972 filter=lfs diff=lfs merge=lfs -text
63
+ onnx__MatMul_4973 filter=lfs diff=lfs merge=lfs -text
64
+ onnx__MatMul_4974 filter=lfs diff=lfs merge=lfs -text
65
+ onnx__MatMul_4975 filter=lfs diff=lfs merge=lfs -text
66
+ onnx__MatMul_4976 filter=lfs diff=lfs merge=lfs -text
67
+ onnx__MatMul_4977 filter=lfs diff=lfs merge=lfs -text
68
+ onnx__MatMul_5002 filter=lfs diff=lfs merge=lfs -text
69
+ onnx__MatMul_5003 filter=lfs diff=lfs merge=lfs -text
70
+ onnx__MatMul_5004 filter=lfs diff=lfs merge=lfs -text
71
+ onnx__MatMul_5005 filter=lfs diff=lfs merge=lfs -text
72
+ onnx__MatMul_5006 filter=lfs diff=lfs merge=lfs -text
73
+ onnx__MatMul_5007 filter=lfs diff=lfs merge=lfs -text
74
+ onnx__MatMul_5008 filter=lfs diff=lfs merge=lfs -text
75
+ onnx__MatMul_5033 filter=lfs diff=lfs merge=lfs -text
76
+ onnx__MatMul_5034 filter=lfs diff=lfs merge=lfs -text
77
+ onnx__MatMul_5035 filter=lfs diff=lfs merge=lfs -text
78
+ onnx__MatMul_5036 filter=lfs diff=lfs merge=lfs -text
79
+ onnx__MatMul_5037 filter=lfs diff=lfs merge=lfs -text
80
+ onnx__MatMul_5038 filter=lfs diff=lfs merge=lfs -text
81
+ onnx__MatMul_5039 filter=lfs diff=lfs merge=lfs -text
82
+ onnx__MatMul_5064 filter=lfs diff=lfs merge=lfs -text
83
+ onnx__MatMul_5065 filter=lfs diff=lfs merge=lfs -text
84
+ onnx__MatMul_5066 filter=lfs diff=lfs merge=lfs -text
85
+ onnx__MatMul_5067 filter=lfs diff=lfs merge=lfs -text
86
+ onnx__MatMul_5068 filter=lfs diff=lfs merge=lfs -text
87
+ onnx__MatMul_5069 filter=lfs diff=lfs merge=lfs -text
88
+ onnx__MatMul_5070 filter=lfs diff=lfs merge=lfs -text
89
+ onnx__MatMul_5095 filter=lfs diff=lfs merge=lfs -text
90
+ onnx__MatMul_5096 filter=lfs diff=lfs merge=lfs -text
91
+ onnx__MatMul_5097 filter=lfs diff=lfs merge=lfs -text
92
+ onnx__MatMul_5098 filter=lfs diff=lfs merge=lfs -text
93
+ onnx__MatMul_5099 filter=lfs diff=lfs merge=lfs -text
94
+ onnx__MatMul_5100 filter=lfs diff=lfs merge=lfs -text
95
+ onnx__MatMul_5101 filter=lfs diff=lfs merge=lfs -text
96
+ onnx__MatMul_5126 filter=lfs diff=lfs merge=lfs -text
97
+ onnx__MatMul_5127 filter=lfs diff=lfs merge=lfs -text
98
+ onnx__MatMul_5128 filter=lfs diff=lfs merge=lfs -text
99
+ onnx__MatMul_5129 filter=lfs diff=lfs merge=lfs -text
100
+ onnx__MatMul_5130 filter=lfs diff=lfs merge=lfs -text
101
+ onnx__MatMul_5131 filter=lfs diff=lfs merge=lfs -text
102
+ onnx__MatMul_5132 filter=lfs diff=lfs merge=lfs -text
103
+ onnx__MatMul_5157 filter=lfs diff=lfs merge=lfs -text
104
+ onnx__MatMul_5158 filter=lfs diff=lfs merge=lfs -text
105
+ onnx__MatMul_5159 filter=lfs diff=lfs merge=lfs -text
106
+ onnx__MatMul_5160 filter=lfs diff=lfs merge=lfs -text
107
+ onnx__MatMul_5161 filter=lfs diff=lfs merge=lfs -text
108
+ onnx__MatMul_5162 filter=lfs diff=lfs merge=lfs -text
109
+ onnx__MatMul_5163 filter=lfs diff=lfs merge=lfs -text
110
+ onnx__MatMul_5188 filter=lfs diff=lfs merge=lfs -text
111
+ onnx__MatMul_5189 filter=lfs diff=lfs merge=lfs -text
112
+ onnx__MatMul_5190 filter=lfs diff=lfs merge=lfs -text
113
+ onnx__MatMul_5191 filter=lfs diff=lfs merge=lfs -text
114
+ onnx__MatMul_5192 filter=lfs diff=lfs merge=lfs -text
115
+ onnx__MatMul_5193 filter=lfs diff=lfs merge=lfs -text
116
+ onnx__MatMul_5194 filter=lfs diff=lfs merge=lfs -text
117
+ onnx__MatMul_5219 filter=lfs diff=lfs merge=lfs -text
118
+ onnx__MatMul_5220 filter=lfs diff=lfs merge=lfs -text
119
+ onnx__MatMul_5221 filter=lfs diff=lfs merge=lfs -text
120
+ onnx__MatMul_5222 filter=lfs diff=lfs merge=lfs -text
121
+ onnx__MatMul_5223 filter=lfs diff=lfs merge=lfs -text
122
+ onnx__MatMul_5224 filter=lfs diff=lfs merge=lfs -text
123
+ onnx__MatMul_5225 filter=lfs diff=lfs merge=lfs -text
124
+ onnx__MatMul_5250 filter=lfs diff=lfs merge=lfs -text
125
+ onnx__MatMul_5251 filter=lfs diff=lfs merge=lfs -text
126
+ onnx__MatMul_5252 filter=lfs diff=lfs merge=lfs -text
127
+ onnx__MatMul_5253 filter=lfs diff=lfs merge=lfs -text
128
+ onnx__MatMul_5254 filter=lfs diff=lfs merge=lfs -text
129
+ onnx__MatMul_5255 filter=lfs diff=lfs merge=lfs -text
130
+ onnx__MatMul_5256 filter=lfs diff=lfs merge=lfs -text
131
+ onnx__MatMul_5281 filter=lfs diff=lfs merge=lfs -text
132
+ onnx__MatMul_5282 filter=lfs diff=lfs merge=lfs -text
133
+ onnx__MatMul_5283 filter=lfs diff=lfs merge=lfs -text
134
+ onnx__MatMul_5284 filter=lfs diff=lfs merge=lfs -text
135
+ onnx__MatMul_5285 filter=lfs diff=lfs merge=lfs -text
136
+ onnx__MatMul_5286 filter=lfs diff=lfs merge=lfs -text
137
+ onnx__MatMul_5287 filter=lfs diff=lfs merge=lfs -text
138
+ onnx__MatMul_5312 filter=lfs diff=lfs merge=lfs -text
139
+ onnx__MatMul_5313 filter=lfs diff=lfs merge=lfs -text
140
+ onnx__MatMul_5314 filter=lfs diff=lfs merge=lfs -text
141
+ onnx__MatMul_5315 filter=lfs diff=lfs merge=lfs -text
142
+ onnx__MatMul_5316 filter=lfs diff=lfs merge=lfs -text
143
+ onnx__MatMul_5317 filter=lfs diff=lfs merge=lfs -text
144
+ onnx__MatMul_5318 filter=lfs diff=lfs merge=lfs -text
145
+ onnx__MatMul_5343 filter=lfs diff=lfs merge=lfs -text
146
+ onnx__MatMul_5344 filter=lfs diff=lfs merge=lfs -text
147
+ onnx__MatMul_5345 filter=lfs diff=lfs merge=lfs -text
148
+ onnx__MatMul_5346 filter=lfs diff=lfs merge=lfs -text
149
+ onnx__MatMul_5347 filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "transformers_version": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }
model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1602ecf8f4e69be360b87191d1a4f6aa4b3fa26002ebf0ea058208613737400
3
+ size 1050673152
model.layers.0.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.0.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.1.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.1.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.10.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.10.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.11.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.11.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.12.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.12.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.13.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.13.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.14.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.14.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.15.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.15.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.2.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.2.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.3.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.3.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.4.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.4.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.5.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.5.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.6.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.6.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.7.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.7.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.8.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.8.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.9.input_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.layers.9.post_attention_layernorm.weight ADDED
Binary file (8.19 kB). View file
 
model.norm.weight ADDED
Binary file (8.19 kB). View file
 
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de00f3c44ee01296ce3a3e0f20bd3461dfa99b6425d9715105b6c7653169602
3
+ size 740423
model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4d4d0f0f39c9598f9705b9ea0fce2961e01e81d9e35d169bb2efb8b0e33196
3
+ size 1499820272
onnx__MatMul_4851 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869431fb4450450a00514fb77e83e284e20f854dd5a4880e76104daf2c471080
3
+ size 16777216
onnx__MatMul_4852 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431f2cbec97db388b6418f5d2ecebd1b3f5f64251e52fe783ec5ff6b8c8d3fb2
3
+ size 4194304
onnx__MatMul_4853 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f5807366eaff62f4277305a8a484b141881c7ec4c63325c45633bdff8c33c2
3
+ size 4194304
onnx__MatMul_4878 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac7dba0e3a32a2484ddda89c4d3684d3fbac1fed9c4a95211364e6d4d6ad1e9
3
+ size 16777216
onnx__MatMul_4879 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e5f3763f5b02a07afee4427664989411e612573cbf82430bb8654f69b5679e
3
+ size 67108864
onnx__MatMul_4880 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa73492947348d43c5170e814ef937a8d4439c9f4031e67c25a673c5d9f10e38
3
+ size 67108864
onnx__MatMul_4881 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed407f04ff18c7dfa0fd6d09419b29a505e829a3ad0f4a23d657a0e3f94cc584
3
+ size 67108864
onnx__MatMul_4882 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6807880f8bf7eb67abc4650a0c91c82cdaa4fe9def4df1a54c590d2234f55e3
3
+ size 16777216
onnx__MatMul_4883 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9538cea987084deadb8f5426777c8dfe1bfa3778464b2de74731649e9a5a58be
3
+ size 4194304
onnx__MatMul_4884 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1399dd228cbc451d38f838ea3d8ac7592d318fcd2f18b9f28eaed31d7edece19
3
+ size 4194304
onnx__MatMul_4909 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e974d6c25ae628a24da464727da3c3ba9ae9da3d8e8a22f4c392240dcd73f7
3
+ size 16777216