Hugging Face's logo

TMElyralab
/
lyraBaichuan

English
LLM
baichuan
Model card Files
xet
Community
1
carsonhxsu commited on
Commit
f83cb6b
·
1 Parent(s): fbab0e6

Upload Baichuan2 lyra models

Browse files
Files changed (24) hide show
  1. models/Baichuan2-13B-Base-lyra/1-gpu-fp16.bin +3 -0
  2. models/Baichuan2-13B-Base-lyra/config.ini +14 -0
  3. models/Baichuan2-13B-Base-lyra/config.json +28 -0
  4. models/Baichuan2-13B-Base-lyra/special_tokens_map.json +30 -0
  5. models/Baichuan2-13B-Base-lyra/tokenizer.model +3 -0
  6. models/Baichuan2-13B-Base-lyra/tokenizer_config.json +46 -0
  7. models/Baichuan2-13B-Chat-lyra/1-gpu-fp16.bin +3 -0
  8. models/Baichuan2-13B-Chat-lyra/config.ini +14 -0
  9. models/Baichuan2-13B-Chat-lyra/config.json +29 -0
  10. models/Baichuan2-13B-Chat-lyra/special_tokens_map.json +30 -0
  11. models/Baichuan2-13B-Chat-lyra/tokenizer.model +3 -0
  12. models/Baichuan2-13B-Chat-lyra/tokenizer_config.json +46 -0
  13. models/Baichuan2-7B-Base-lyra/1-gpu-fp16.bin +3 -0
  14. models/Baichuan2-7B-Base-lyra/config.ini +14 -0
  15. models/Baichuan2-7B-Base-lyra/config.json +28 -0
  16. models/Baichuan2-7B-Base-lyra/special_tokens_map.json +30 -0
  17. models/Baichuan2-7B-Base-lyra/tokenizer.model +3 -0
  18. models/Baichuan2-7B-Base-lyra/tokenizer_config.json +36 -0
  19. models/Baichuan2-7B-Chat-lyra/1-gpu-fp16.bin +3 -0
  20. models/Baichuan2-7B-Chat-lyra/config.ini +14 -0
  21. models/Baichuan2-7B-Chat-lyra/config.json +29 -0
  22. models/Baichuan2-7B-Chat-lyra/special_tokens_map.json +30 -0
  23. models/Baichuan2-7B-Chat-lyra/tokenizer.model +3 -0
  24. models/Baichuan2-7B-Chat-lyra/tokenizer_config.json +36 -0
models/Baichuan2-13B-Base-lyra/1-gpu-fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a724276cf0e5e75a72648034c54fe9bcf4b1b9165fbd663cf64f8dd72b0d20
3
+ size 27793336320
models/Baichuan2-13B-Base-lyra/config.ini ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [baichuan]
2
+ model_name = Baichuan2_13B
3
+ head_num = 40
4
+ size_per_head = 128
5
+ inter_size = 13696
6
+ num_layer = 40
7
+ rotary_embedding = 128
8
+ layernorm_eps = 1e-06
9
+ vocab_size = 125696
10
+ start_id = 1
11
+ end_id = 2
12
+ tensor_para_size = 1
13
+ weight_data_type = fp16
14
+
models/Baichuan2-13B-Base-lyra/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "architectures": [
4
+ "BaichuanForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_baichuan.BaichuanConfig",
8
+ "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 13696,
17
+ "model_max_length": 4096,
18
+ "model_type": "baichuan",
19
+ "num_attention_heads": 40,
20
+ "num_hidden_layers": 40,
21
+ "pad_token_id": 0,
22
+ "rms_norm_eps": 1e-06,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.29.2",
26
+ "use_cache": true,
27
+ "vocab_size": 125696
28
+ }
models/Baichuan2-13B-Base-lyra/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": true
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": true
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": true
22
+ },
23
+ "pad_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": true
29
+ }
30
+ }
models/Baichuan2-13B-Base-lyra/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
3
+ size 2001107
models/Baichuan2-13B-Base-lyra/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "auto_map": {
5
+ "AutoTokenizer": [
6
+ "tokenization_baichuan.BaichuanTokenizer",
7
+ null
8
+ ]
9
+ },
10
+ "bos_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": true
17
+ },
18
+ "clean_up_tokenization_spaces": false,
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": true
26
+ },
27
+ "model_max_length": 4096,
28
+ "pad_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": true
35
+ },
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "BaichuanTokenizer",
38
+ "unk_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": true
45
+ }
46
+ }
models/Baichuan2-13B-Chat-lyra/1-gpu-fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182aeae174da2d23af945c93ab92a6ba48ccf9bbc02474096ba950dd7e17bdd2
3
+ size 27793336320
models/Baichuan2-13B-Chat-lyra/config.ini ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [baichuan]
2
+ model_name = Baichuan2_13B_chat
3
+ head_num = 40
4
+ size_per_head = 128
5
+ inter_size = 13696
6
+ num_layer = 40
7
+ rotary_embedding = 128
8
+ layernorm_eps = 1e-06
9
+ vocab_size = 125696
10
+ start_id = 1
11
+ end_id = 2
12
+ tensor_para_size = 1
13
+ weight_data_type = fp16
14
+
models/Baichuan2-13B-Chat-lyra/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "architectures": [
4
+ "BaichuanForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_baichuan.BaichuanConfig",
8
+ "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
9
+ },
10
+ "tokenizer_class": "BaichuanTokenizer",
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "gradient_checkpointing": false,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 5120,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 13696,
18
+ "model_max_length": 4096,
19
+ "model_type": "baichuan",
20
+ "num_attention_heads": 40,
21
+ "num_hidden_layers": 40,
22
+ "pad_token_id": 0,
23
+ "rms_norm_eps": 1e-06,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.29.2",
27
+ "use_cache": true,
28
+ "vocab_size": 125696
29
+ }
models/Baichuan2-13B-Chat-lyra/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": true
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": true
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": true
22
+ },
23
+ "pad_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": true
29
+ }
30
+ }
models/Baichuan2-13B-Chat-lyra/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
3
+ size 2001107
models/Baichuan2-13B-Chat-lyra/tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "auto_map": {
5
+ "AutoTokenizer": [
6
+ "tokenization_baichuan.BaichuanTokenizer",
7
+ null
8
+ ]
9
+ },
10
+ "bos_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": true
17
+ },
18
+ "clean_up_tokenization_spaces": false,
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": true
26
+ },
27
+ "model_max_length": 4096,
28
+ "pad_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": true
35
+ },
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "BaichuanTokenizer",
38
+ "unk_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": true
45
+ }
46
+ }
models/Baichuan2-7B-Base-lyra/1-gpu-fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f074fb8499ce485f787b8452d33d3c57c7fa3e6b624688c7b668013278871034
3
+ size 15011946496
models/Baichuan2-7B-Base-lyra/config.ini ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [baichuan]
2
+ model_name = Baichuan2_7B
3
+ head_num = 32
4
+ size_per_head = 128
5
+ inter_size = 11008
6
+ num_layer = 32
7
+ rotary_embedding = 128
8
+ layernorm_eps = 1e-06
9
+ vocab_size = 125696
10
+ start_id = 1
11
+ end_id = 2
12
+ tensor_para_size = 1
13
+ weight_data_type = fp16
14
+
models/Baichuan2-7B-Base-lyra/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BaichuanForCausalLM"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "configuration_baichuan.BaichuanConfig",
7
+ "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
8
+ },
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 4096,
16
+ "model_max_length": 4096,
17
+ "model_type": "baichuan",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "_from_model_config": true,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.29.2",
26
+ "use_cache": true,
27
+ "vocab_size": 125696
28
+ }
models/Baichuan2-7B-Base-lyra/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
models/Baichuan2-7B-Base-lyra/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
3
+ size 2001107
models/Baichuan2-7B-Base-lyra/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": ["tokenization_baichuan.BaichuanTokenizer", null]
4
+ },
5
+ "add_bos_token": false,
6
+ "add_eos_token": false,
7
+ "use_fast": false,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": {
10
+ "__type": "AddedToken",
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": true
16
+ },
17
+ "model_max_length": 4096,
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "BaichuanTokenizer",
20
+ "pad_token": {
21
+ "__type": "AddedToken",
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": true
27
+ },
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": true
35
+ }
36
+ }
models/Baichuan2-7B-Chat-lyra/1-gpu-fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1ed832acfd64d2e30216fbf3b4ce40b453b22cef2f59481810e4bed79f8d18
3
+ size 15011946496
models/Baichuan2-7B-Chat-lyra/config.ini ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [baichuan]
2
+ model_name = Baichuan2_7B_chat
3
+ head_num = 32
4
+ size_per_head = 128
5
+ inter_size = 11008
6
+ num_layer = 32
7
+ rotary_embedding = 128
8
+ layernorm_eps = 1e-06
9
+ vocab_size = 125696
10
+ start_id = 1
11
+ end_id = 2
12
+ tensor_para_size = 1
13
+ weight_data_type = fp16
14
+
models/Baichuan2-7B-Chat-lyra/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BaichuanForCausalLM"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "configuration_baichuan.BaichuanConfig",
7
+ "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
8
+ },
9
+ "tokenizer_class": "BaichuanTokenizer",
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 11008,
16
+ "max_position_embeddings": 4096,
17
+ "model_max_length": 4096,
18
+ "model_type": "baichuan",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "pad_token_id": 0,
22
+ "rms_norm_eps": 1e-06,
23
+ "_from_model_config": true,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.29.2",
27
+ "use_cache": true,
28
+ "vocab_size": 125696
29
+ }
models/Baichuan2-7B-Chat-lyra/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
models/Baichuan2-7B-Chat-lyra/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
3
+ size 2001107
models/Baichuan2-7B-Chat-lyra/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": ["tokenization_baichuan.BaichuanTokenizer", null]
4
+ },
5
+ "add_bos_token": false,
6
+ "add_eos_token": false,
7
+ "use_fast": false,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": {
10
+ "__type": "AddedToken",
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": true
16
+ },
17
+ "model_max_length": 4096,
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "BaichuanTokenizer",
20
+ "pad_token": {
21
+ "__type": "AddedToken",
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": true
27
+ },
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": true
35
+ }
36
+ }