Hugging Face's logo

MultiLlasa
/
Llasa-1B-Multilingual-German

Safetensors
German
llama
Model card Files Community
1
SebastianBodza commited on
Commit
aed8093
·
verified ·
1 Parent(s): 63c0709

Add files using upload-large-folder tool

Browse files
Files changed (46) hide show
  1. .gitattributes +8 -0
  2. checkpoint-10989/config.json +40 -0
  3. checkpoint-10989/generation_config.json +12 -0
  4. checkpoint-10989/model.safetensors +3 -0
  5. checkpoint-10989/optimizer.pt +3 -0
  6. checkpoint-10989/rng_state_0.pth +3 -0
  7. checkpoint-10989/rng_state_1.pth +3 -0
  8. checkpoint-10989/rng_state_2.pth +3 -0
  9. checkpoint-10989/rng_state_3.pth +3 -0
  10. checkpoint-10989/scheduler.pt +3 -0
  11. checkpoint-10989/special_tokens_map.json +17 -0
  12. checkpoint-10989/tokenizer.json +3 -0
  13. checkpoint-10989/tokenizer_config.json +3 -0
  14. checkpoint-10989/trainer_state.json +0 -0
  15. checkpoint-10989/training_args.bin +3 -0
  16. checkpoint-11988/config.json +40 -0
  17. checkpoint-11988/generation_config.json +12 -0
  18. checkpoint-11988/model.safetensors +3 -0
  19. checkpoint-11988/optimizer.pt +3 -0
  20. checkpoint-11988/rng_state_0.pth +3 -0
  21. checkpoint-11988/rng_state_1.pth +3 -0
  22. checkpoint-11988/rng_state_2.pth +3 -0
  23. checkpoint-11988/rng_state_3.pth +3 -0
  24. checkpoint-11988/scheduler.pt +3 -0
  25. checkpoint-11988/special_tokens_map.json +17 -0
  26. checkpoint-11988/tokenizer.json +3 -0
  27. checkpoint-11988/tokenizer_config.json +3 -0
  28. checkpoint-11988/trainer_state.json +0 -0
  29. checkpoint-11988/training_args.bin +3 -0
  30. checkpoint-9990/config.json +40 -0
  31. checkpoint-9990/generation_config.json +12 -0
  32. checkpoint-9990/model.safetensors +3 -0
  33. checkpoint-9990/optimizer.pt +3 -0
  34. checkpoint-9990/rng_state_0.pth +3 -0
  35. checkpoint-9990/rng_state_1.pth +3 -0
  36. checkpoint-9990/rng_state_2.pth +3 -0
  37. checkpoint-9990/rng_state_3.pth +3 -0
  38. checkpoint-9990/scheduler.pt +3 -0
  39. checkpoint-9990/special_tokens_map.json +17 -0
  40. checkpoint-9990/tokenizer.json +3 -0
  41. checkpoint-9990/tokenizer_config.json +3 -0
  42. checkpoint-9990/trainer_state.json +0 -0
  43. checkpoint-9990/training_args.bin +3 -0
  44. special_tokens_map.json +17 -0
  45. tokenizer.json +3 -0
  46. tokenizer_config.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,11 @@ 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
+ checkpoint-9990/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-10989/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-11988/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
40
+ 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
checkpoint-10989/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-10989/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-10989/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edbc5d6a59d1f579bf4cb4001bdae6e50546c5b1b6b1ebff471278398d8e26c7
3
+ size 2740113872
checkpoint-10989/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65230d51460bb20815c47c619870667570176a2a2418b17fc8eb42c129b7b57
3
+ size 5480320942
checkpoint-10989/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6d1d381278fb22b22bfd8330681970ee2403fa0d0b445b2ee7a21b7f082f9f
3
+ size 15024
checkpoint-10989/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0178e3284ccbfd37ac137f698b5f99a9e7d27de640fdfe23cf8fa488b77d5395
3
+ size 15024
checkpoint-10989/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7bec3b6fff9b26029e4109665d06520223e4667ca532d843849539f6c81b589
3
+ size 15024
checkpoint-10989/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e252f8fd1f83562b36f69fd209feb4eb1542571be5a4e8ac315090db3730fd59
3
+ size 15024
checkpoint-10989/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e31c0a73dd93ca495bc0a74af5563f04de0697e5158a6917a5467b8fb542aa5
3
+ size 1064
checkpoint-10989/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-10989/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d92f3dbf3c23d734e6356241cef149b42fe79848176a54145b6f9a886fd73b
3
+ size 29521206
checkpoint-10989/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-10989/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10989/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089b58f069d2fc49b7875c2d04f364dad8873f35aaa15889bbb70e8f374c8bf4
3
+ size 5432
checkpoint-11988/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-11988/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-11988/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf45ffa0820a407501f6361cc7e49657e339ca9862502d3901a1d6e478b7c1b4
3
+ size 2740113872
checkpoint-11988/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232ad0212692ad67a2130315c7dccdb7e7f1881d21c76073af58484d0a1e8969
3
+ size 5480320942
checkpoint-11988/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca6265e8e2262bb5c15a70d21454a6b211b9b2d32d9dc8148906e78ea170eaf
3
+ size 15024
checkpoint-11988/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d7aae23c0ad281a5723c42d3d0c2b4dad0be21eba7d073650ee2fc41e43602
3
+ size 15024
checkpoint-11988/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465be5b0a5af7606f9f257a8f2d7c4169c76acb06f8360d1e9ee648b1a569c0e
3
+ size 15024
checkpoint-11988/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0ec1844e355f804002cdc7088f40050d1244340689686f1b8dadac9301738f
3
+ size 15024
checkpoint-11988/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1ae34a2c530c2bace1a13db2d90698a935428b3aa25b8be38d362162e1f72f
3
+ size 1064
checkpoint-11988/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-11988/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d92f3dbf3c23d734e6356241cef149b42fe79848176a54145b6f9a886fd73b
3
+ size 29521206
checkpoint-11988/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-11988/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11988/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089b58f069d2fc49b7875c2d04f364dad8873f35aaa15889bbb70e8f374c8bf4
3
+ size 5432
checkpoint-9990/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-9990/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-9990/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812dfd372979218787af53e6bd78c70fa24d4931b4cba1d2c1659d84a3fe6a7e
3
+ size 2740113872
checkpoint-9990/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edc0ce469772a4fc39f5c5390efef7c658521c448c28499234f1cd9a2ea7195
3
+ size 5480320942
checkpoint-9990/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727a29225b3a57083df6716f89d12c226f440fba33b2cf3a11cc14fc56415bee
3
+ size 15024
checkpoint-9990/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19196062cac6851e7878550f3ec18df650454294f22a73327cd60bb311d5ca3
3
+ size 15024
checkpoint-9990/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7af4b14a44a7c67224cb1f18ec389134691f8634f287e688088f6a77ce1c429
3
+ size 15024
checkpoint-9990/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8425db93d8404ce5c39c969d20421626b818c961f184172ec3765868123dae2
3
+ size 15024
checkpoint-9990/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d71093b013ac39e5d757049d80833036773c1d2ab19f549a6897512d29eee3
3
+ size 1064
checkpoint-9990/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-9990/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d92f3dbf3c23d734e6356241cef149b42fe79848176a54145b6f9a886fd73b
3
+ size 29521206
checkpoint-9990/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-9990/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-9990/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089b58f069d2fc49b7875c2d04f364dad8873f35aaa15889bbb70e8f374c8bf4
3
+ size 5432
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": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d92f3dbf3c23d734e6356241cef149b42fe79848176a54145b6f9a886fd73b
3
+ size 29521206
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1ba0909d80bd18ffa22e8c05ebf509ae17b5b85d6e31e7a00bb11a1700cdd5
3
+ size 11710509