hieptuyet1102 commited on
Commit
61a0aa3
1 Parent(s): cec450f

Training in progress, step 1000

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|extra_0|>": 151646,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hieptuyet1102/stage2-llavaqwen1.5-0.5B-vista-5ep",
3
+ "architectures": [
4
+ "MoELLaVAQwen1_5ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "freeze_mm_mlp_adapter": false,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "image_aspect_ratio": "pad",
13
+ "image_projector_type": "mlp2x_gelu",
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2816,
16
+ "lora": {},
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 21,
19
+ "mm_hidden_size": 768,
20
+ "mm_image_tower": "google/siglip-base-patch16-256-multilingual",
21
+ "mm_projector_lr": null,
22
+ "mm_use_im_patch_token": false,
23
+ "mm_use_im_start_end": false,
24
+ "mm_video_tower": null,
25
+ "mm_vision_select_feature": "patch",
26
+ "mm_vision_select_layer": -2,
27
+ "model_type": "moe_llava_qwen1_5",
28
+ "moe": {
29
+ "capacity_factor": 1.5,
30
+ "ep_size": 1,
31
+ "eval_capacity_factor": 2.0,
32
+ "min_capacity": 0,
33
+ "moe_enable": true,
34
+ "moe_layers_idx": [
35
+ 0,
36
+ 2,
37
+ 4,
38
+ 6,
39
+ 8,
40
+ 10,
41
+ 12,
42
+ 14,
43
+ 16,
44
+ 18,
45
+ 20,
46
+ 22
47
+ ],
48
+ "moe_mode": "sparse",
49
+ "num_experts": [
50
+ 4,
51
+ 4,
52
+ 4,
53
+ 4,
54
+ 4,
55
+ 4,
56
+ 4,
57
+ 4,
58
+ 4,
59
+ 4,
60
+ 4,
61
+ 4
62
+ ],
63
+ "router_aux_loss_coef": 0.01,
64
+ "top_k_experts": 2,
65
+ "train_modules": [
66
+ "mlp.gate_proj",
67
+ "mlp.up_proj",
68
+ "mlp.down_proj",
69
+ "wg"
70
+ ],
71
+ "use_residual": false
72
+ },
73
+ "num_attention_heads": 16,
74
+ "num_hidden_layers": 24,
75
+ "num_key_value_heads": 16,
76
+ "pad_token_id": 151646,
77
+ "rms_norm_eps": 1e-06,
78
+ "rope_theta": 1000000.0,
79
+ "sliding_window": 32768,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_padding_side": "right",
82
+ "torch_dtype": "float16",
83
+ "transformers_version": "4.37.0",
84
+ "tune_mm_mlp_adapter": false,
85
+ "use_cache": false,
86
+ "use_mm_proj": true,
87
+ "use_sliding_window": false,
88
+ "video_global_proj": false,
89
+ "video_projector_type": "linear",
90
+ "video_spatial_proj": false,
91
+ "video_temproal_proj": false,
92
+ "vocab_size": 151646
93
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e255b4ed885b421200e1cc4b21493b4442078a605451c62f861169420f034ed
3
+ size 4100964168
special_tokens_map.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|extra_0|>",
14
+ "unk_token": {
15
+ "content": "<|extra_0|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ }
21
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|extra_0|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|endoftext|>",
45
+ "errors": "replace",
46
+ "model_max_length": 2048,
47
+ "pad_token": "<|extra_0|>",
48
+ "padding_side": "right",
49
+ "split_special_tokens": false,
50
+ "tokenizer_class": "Qwen2Tokenizer",
51
+ "unk_token": "<|extra_0|>"
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487d19bdedf84da186afd1b2df1ad213c4e92d6c528b0b6b60a5cacd6cf0fdfd
3
+ size 5947
vocab.json ADDED
The diff for this file is too large to render. See raw diff