Hugging Face's logo

iisys-hof
/
OLaPhLLM_v2

Translation
Transformers
Safetensors
gemma2
text-generation
text-generation-inference
Model card Files
xet
 Community
ojo commited on
Commit
c344246
·
verified ·
1 Parent(s): cf62078

Upload 14 files

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. all_results.json +12 -0
  3. chat_template.jinja +1 -0
  4. config.json +65 -0
  5. eval_results.json +7 -0
  6. generation_config.json +11 -0
  7. model.safetensors +3 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +18 -0
  10. train_results.json +8 -0
  11. trainer_log.jsonl +0 -0
  12. trainer_state.json +0 -0
  13. training_args.bin +3 -0
  14. training_eval_loss.png +0 -0
  15. training_loss.png +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.013834569603204727,
4
+ "eval_runtime": 613.8852,
5
+ "eval_samples_per_second": 110.77,
6
+ "eval_steps_per_second": 6.923,
7
+ "total_flos": 3635036937584640.0,
8
+ "train_loss": 0.040250375388965885,
9
+ "train_runtime": 214343.3461,
10
+ "train_samples_per_second": 31.725,
11
+ "train_steps_per_second": 0.496
12
+ }
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": 50.0,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 2304,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 9216,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "full_attention"
46
+ ],
47
+ "max_position_embeddings": 8192,
48
+ "model_type": "gemma2",
49
+ "num_attention_heads": 8,
50
+ "num_hidden_layers": 26,
51
+ "num_key_value_heads": 4,
52
+ "pad_token_id": 0,
53
+ "query_pre_attn_scalar": 256,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "rope_theta": 10000.0,
57
+ "rope_type": "default"
58
+ },
59
+ "sliding_window": 4096,
60
+ "tie_word_embeddings": true,
61
+ "transformers_version": "5.0.0",
62
+ "use_bidirectional_attention": null,
63
+ "use_cache": false,
64
+ "vocab_size": 256064
65
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 0.013834569603204727,
4
+ "eval_runtime": 613.8852,
5
+ "eval_samples_per_second": 110.77,
6
+ "eval_steps_per_second": 6.923
7
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 1
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "5.0.0",
10
+ "use_cache": true
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc73ef51d53b5cd15a8d0c5b2d660186e65ad303e1488fcf3caa8f79410305a
3
+ size 5229012424
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09888eecfc2c471e752492bac14515a6f6e0af75dac67698f274234538a9b20
3
+ size 34374269
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<eos>",
6
+ "is_local": true,
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "model_specific_special_tokens": {},
10
+ "pad_token": "<pad>",
11
+ "padding_side": "right",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "split_special_tokens": false,
15
+ "tokenizer_class": "GemmaTokenizer",
16
+ "unk_token": "<unk>",
17
+ "use_default_system_prompt": false
18
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 3635036937584640.0,
4
+ "train_loss": 0.040250375388965885,
5
+ "train_runtime": 214343.3461,
6
+ "train_samples_per_second": 31.725,
7
+ "train_steps_per_second": 0.496
8
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d5e9864c0480c6ce77f22859a347fb92ca258c36b5a77321ffb918fd2e7355
3
+ size 7313
training_eval_loss.png ADDED
training_loss.png ADDED