Hugging Face's logo

MultiLlasa
/
Llasa-1B-Multilingual-German

Safetensors
German
llama
Model card Files Community
1
SebastianBodza commited on
Commit
19412e6
·
verified ·
1 Parent(s): aed8093

Add files using upload-large-folder tool

Browse files
Files changed (26) hide show
  1. .gitattributes +2 -0
  2. checkpoint-12947/config.json +40 -0
  3. checkpoint-12947/generation_config.json +12 -0
  4. checkpoint-12947/model.safetensors +3 -0
  5. checkpoint-12947/optimizer.pt +3 -0
  6. checkpoint-12947/rng_state_0.pth +3 -0
  7. checkpoint-12947/rng_state_1.pth +3 -0
  8. checkpoint-12947/rng_state_2.pth +3 -0
  9. checkpoint-12947/rng_state_3.pth +3 -0
  10. checkpoint-12947/scheduler.pt +3 -0
  11. checkpoint-12947/special_tokens_map.json +17 -0
  12. checkpoint-12947/tokenizer.json +3 -0
  13. checkpoint-12947/tokenizer_config.json +3 -0
  14. checkpoint-12947/trainer_state.json +0 -0
  15. checkpoint-12947/training_args.bin +3 -0
  16. config copy.json +40 -0
  17. config.json +40 -0
  18. generation_config copy.json +12 -0
  19. generation_config.json +12 -0
  20. model.safetensors +3 -0
  21. special_tokens_map copy.json +17 -0
  22. special_tokens_map.json +1 -1
  23. tokenizer copy.json +3 -0
  24. tokenizer_config copy.json +3 -0
  25. tokenizer_config.json +2 -2
  26. trainer_state.json +0 -0
.gitattributes CHANGED
@@ -41,3 +41,5 @@ checkpoint-10989/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  checkpoint-11988/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  checkpoint-9990/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
41
  checkpoint-11988/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  checkpoint-9990/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ tokenizer[[:space:]]copy.json filter=lfs diff=lfs merge=lfs -text
45
+ tokenizer_config[[:space:]]copy.json filter=lfs diff=lfs merge=lfs -text
checkpoint-12947/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/user/LLaSA_training/output/checkpoint-6993",
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
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.48.3",
38
+ "use_cache": true,
39
+ "vocab_size": 193800
40
+ }
checkpoint-12947/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": "4.48.3"
12
+ }
checkpoint-12947/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f8227c8be13f344ec6942d5cc9adb89fe569ec8c650762c8329705813155e5
3
+ size 2740113872
checkpoint-12947/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8695bd76a4dbd4736fff4f593158bac27abbfef6a0fb8e45266c1df9d73dd5
3
+ size 5480320942
checkpoint-12947/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff1ab8f3dd242cffca42d99b4839aceabdaa5c2818c2130ae63731e44083b1d
3
+ size 15024
checkpoint-12947/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc64dfd39835f3bea15abb928e316f02d6f74788888d6bf04fde7b6cdd920b3
3
+ size 15024
checkpoint-12947/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494d18887b0bf36611c08a208f6fb23940b28bd44f487f94d6399d2a72e1ea9e
3
+ size 15024
checkpoint-12947/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192db7c06c8fe19349c939fc49d978ec71681f7e980b03123ed10b58e601abe8
3
+ size 15024
checkpoint-12947/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d079ae34b072e833b96c952d63071d9adc286f0b4f0398b6749bac84ef1d8cc
3
+ size 1064
checkpoint-12947/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
checkpoint-12947/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d92f3dbf3c23d734e6356241cef149b42fe79848176a54145b6f9a886fd73b
3
+ size 29521206
checkpoint-12947/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c494500e8d6ec069de7d95f2948aec356a9618c746f8b8e23905d3a3685607
3
+ size 11710504
checkpoint-12947/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12947/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089b58f069d2fc49b7875c2d04f364dad8873f35aaa15889bbb70e8f374c8bf4
3
+ size 5432
config copy.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/user/LLaSA_training/output/checkpoint-6993",
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
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.48.3",
38
+ "use_cache": true,
39
+ "vocab_size": 193800
40
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/user/LLaSA_training/output/checkpoint-6993",
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
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.48.3",
38
+ "use_cache": true,
39
+ "vocab_size": 193800
40
+ }
generation_config copy.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": "4.48.3"
12
+ }
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": "4.48.3"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f8227c8be13f344ec6942d5cc9adb89fe569ec8c650762c8329705813155e5
3
+ size 2740113872
special_tokens_map copy.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
special_tokens_map.json CHANGED
@@ -13,5 +13,5 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|end_of_text|>"
17
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|eot_id|>"
17
  }
tokenizer copy.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d92f3dbf3c23d734e6356241cef149b42fe79848176a54145b6f9a886fd73b
3
+ size 29521206
tokenizer_config copy.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c494500e8d6ec069de7d95f2948aec356a9618c746f8b8e23905d3a3685607
3
+ size 11710504
tokenizer_config.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d1ba0909d80bd18ffa22e8c05ebf509ae17b5b85d6e31e7a00bb11a1700cdd5
3
- size 11710509
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c494500e8d6ec069de7d95f2948aec356a9618c746f8b8e23905d3a3685607
3
+ size 11710504
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff